# Positronick Soul Hub > Curated gallery and registry of installable agent-personality files (SOUL.md), plus AI tools, CLIs, MCP servers, agents, skills, plugins and loops published by verified authors. Install the CLI: `curl -fsSL https://positronick.com/install.sh | sh` — then `positronick soul install ` or `positronick soul search ` Direct (no CLI): `curl https://positronick.com/api/souls/.md > ~/.hermes/SOUL.md` ## Souls - [Devils Advocate](https://positronick.com/souls/devils-advocate): A relentless devils advocate who stress-tests your thinking. — raw: https://positronick.com/api/souls/devils-advocate.md - [Language Coach](https://positronick.com/souls/language-coach): A friendly coach for daily conversational language practice. — raw: https://positronick.com/api/souls/language-coach.md - [DevOps / SRE](https://positronick.com/souls/devops-sre): An SRE who automates everything and treats reliability as a feature. — raw: https://positronick.com/api/souls/devops-sre.md - [Dungeon Master](https://positronick.com/souls/dungeon-master): A vivid dungeon master who runs improv tabletop adventures. — raw: https://positronick.com/api/souls/dungeon-master.md - [Executive Assistant](https://positronick.com/souls/executive-assistant): A proactive assistant who guards your time and never drops a ball. — raw: https://positronick.com/api/souls/executive-assistant.md - [Data Analyst](https://positronick.com/souls/data-analyst): A skeptical analyst who interrogates every number before trusting it. — raw: https://positronick.com/api/souls/data-analyst.md - [Brand Strategist](https://positronick.com/souls/brand-strategist): A strategist who finds the sharp, ownable angle for a brand. — raw: https://positronick.com/api/souls/brand-strategist.md - [Copywriter](https://positronick.com/souls/copywriter): A punchy copywriter who writes like a human, not a brochure. — raw: https://positronick.com/api/souls/copywriter.md - [Mindful Companion](https://positronick.com/souls/mindful-companion): A calm, grounded companion for reflection and focus. — raw: https://positronick.com/api/souls/mindful-companion.md - [Socratic Tutor](https://positronick.com/souls/socratic-tutor): A patient tutor who teaches by asking, not telling. — raw: https://positronick.com/api/souls/socratic-tutor.md - [Red Team Agent](https://positronick.com/souls/red-team-agent): A security red-teamer who probes for weaknesses — authorized use only. — raw: https://positronick.com/api/souls/red-team-agent.md - [Senior Backend Engineer](https://positronick.com/souls/senior-backend-engineer): A pragmatic senior backend engineer who ships clean, tested services. — raw: https://positronick.com/api/souls/senior-backend-engineer.md - [Positronick Principles](https://positronick.com/souls/positronick-principles): Thirteen numbered rules of engineering discipline — verify before you assert, test before you code, fail loud, and cite the rule you applied. — raw: https://positronick.com/api/souls/positronick-principles.md - [Literature Reviewer](https://positronick.com/souls/literature-reviewer): A meticulous research assistant who summarizes and cites, never invents. — raw: https://positronick.com/api/souls/literature-reviewer.md - [Code Reviewer](https://positronick.com/souls/code-reviewer): A rigorous reviewer who catches bugs, security holes, and unclear code. — raw: https://positronick.com/api/souls/code-reviewer.md - [Product Manager](https://positronick.com/souls/product-manager): A decisive PM who turns fuzzy ideas into shipped, measurable outcomes. — raw: https://positronick.com/api/souls/product-manager.md ## Registry - [Agent Skills](https://positronick.com/listings/agent-skills): skill — Anthropic's public repository of Agent Skills: self-contained folders with a SKILL.md that Claude loads dynamically to perform specialized tasks like document creation and MCP server generation. - [DRY on Third Repetition](https://positronick.com/listings/dry-on-third-repetition): loop — Extract a shared unit only where the same logic appears three or more times — and inline back any abstraction used only once or twice. - [Positronick CLI](https://positronick.com/listings/positronick-cli): cli — Find, inspect and install souls, MCP servers and agent tooling from positronick.com — straight from your terminal. - [PostgREST MCP Server (@supabase/mcp-server-postgrest)](https://positronick.com/listings/postgrest-mcp-server-supabasemcp-server-postgrest): mcp — Official MCP server that lets LLMs perform CRUD operations over a Supabase/PostgREST REST API and convert SQL queries to PostgREST syntax, ideal for connecting end users to your app's data. - [AWS SAM CLI](https://positronick.com/listings/aws-sam-cli): cli — A command line tool to build, test, debug, and deploy serverless applications using the AWS Serverless Application Model. - [Docker CLI](https://positronick.com/listings/docker-cli): cli — The official Docker command-line interface for building, running, and managing containers, images, networks, and volumes against the Docker daemon. - [Docker Agent](https://positronick.com/listings/docker-agent): agent — Open-source 'docker agent' builder and runtime for declaring, running, and sharing multi-agent AI teams via YAML, with MCP tools and any LLM provider (formerly named cagent). - [Docker MCP Gateway](https://positronick.com/listings/docker-mcp-gateway): mcp — Open-source 'docker mcp' CLI plugin and gateway that orchestrates Model Context Protocol servers as isolated containers, with secrets, OAuth, and access control, powering Docker Desktop's MCP Toolkit and catalog. - [pi](https://positronick.com/listings/pi): harness — A self-extensible coding-agent harness and AI agent toolkit: an interactive coding agent CLI with a unified multi-provider LLM API, TUI, and web UI libraries. - [GitHub CLI](https://positronick.com/listings/github-cli): cli — GitHub's official command-line tool for working with pull requests, issues, releases, and the GitHub API from the terminal. - [Frontend Design](https://positronick.com/listings/frontend-design): skill — Create distinctive, production-grade frontend interfaces with high design quality — components, pages, and full applications. - [AWS MCP Servers](https://positronick.com/listings/aws-mcp-servers): mcp — An official open-source suite of Model Context Protocol servers connecting AI assistants to AWS services, docs, and infrastructure. - [Genkit](https://positronick.com/listings/genkit): cli — Open-source framework (with CLI and local dev UI) by Google's Firebase for building AI-powered and agentic apps in JavaScript, Go, and Python with a unified model interface, flows, and RAG. - [Firebase CLI](https://positronick.com/listings/firebase-cli): cli — Official command-line interface for Firebase to initialize, test, manage, and deploy Firebase projects, Cloud Functions, hosting, and AI/Genkit features. - [Ask Me Questions](https://positronick.com/listings/ask-me-questions): skill — Systematic requirements discovery through focused multi-round questioning before any code gets written — asking only what the code can't reveal. - [Babysit](https://positronick.com/listings/babysit): skill — Drive a GitHub PR to a fresh approval, green CI, and a mergeable state — verifying every review finding against the code, fixing the real ones, and pushing back with evidence on the rest. - [Reflect](https://positronick.com/listings/reflect): skill — Distill a coding session's hard-won lessons — gotchas, patterns, integration quirks — into the project's knowledge base, with explicit approval before anything is written. - [Notion MCP Server](https://positronick.com/listings/notion-mcp-server): mcp — Official Notion MCP server giving AI tools secure access to a Notion workspace; a hosted remote variant is offered at https://mcp.notion.com/mcp via OAuth. - [notion-workspace-plugin](https://positronick.com/listings/notion-workspace-plugin): plugin — Official Claude Code plugin that bundles Notion Skills, the Notion MCP server, and slash commands for one-click connection of Claude Code to a Notion workspace. - [TypeScript](https://positronick.com/listings/typescript): cli — Strongly-typed superset of JavaScript that compiles to plain JS via the tsc command-line compiler. - [Playwright MCP](https://positronick.com/listings/playwright-mcp): mcp — MCP server that gives agents structured browser automation via Playwright's accessibility tree. - [markitdown-mcp](https://positronick.com/listings/markitdown-mcp): mcp — MCP server exposing MarkItDown's file-to-Markdown conversion (PDF, Office, images, audio) to agents. - [improve](https://positronick.com/listings/improve): skill — Codebase auditor that writes implementation plans - [Spec Kit (Specify CLI)](https://positronick.com/listings/spec-kit-specify-cli): cli — GitHub's toolkit and Specify CLI for Spec-Driven Development, generating executable specs and slash-command workflows for AI coding agents. - [Ground Every Claim](https://positronick.com/listings/ground-every-claim): loop — Audit a doc, PR description, or answer for unsourced assertions and replace each hedge with a cited artifact — file:line, command output, or URL — until nothing rests on inference. - [Codex CLI](https://positronick.com/listings/codex-cli): harness — Lightweight coding agent from OpenAI that runs locally in your terminal, usable with a ChatGPT plan or API key. - [OpenAI Agents SDK (JS/TS)](https://positronick.com/listings/openai-agents-sdk-jsts): agent — JavaScript/TypeScript framework for building multi-agent and voice agent workflows with handoffs, guardrails, and tracing. - [sentry-cli](https://positronick.com/listings/sentry-cli): cli — The long-standing Rust-based command-line utility for Sentry, used to upload debug symbols and source maps, manage releases, and view issues. - [hf (huggingface_hub CLI)](https://positronick.com/listings/hf-huggingface-hub-cli): cli — The official Python client and `hf` command-line tool for interacting with the Hugging Face Hub (auth, downloading/uploading models, datasets, and Spaces). - [Stripe Link CLI](https://positronick.com/listings/stripe-link-cli): cli — Official CLI and local MCP server that issues secure single-use Link payment credentials so AI agents can make approved purchases on your behalf without exposing real card details. - [Supabase CLI](https://positronick.com/listings/supabase-cli): cli — Official CLI to run the full Supabase stack locally, manage Postgres migrations, deploy edge functions, run backups, and generate types from your schema. - [AI SDK](https://positronick.com/listings/ai-sdk): cli — Provider-agnostic TypeScript toolkit for building AI-powered applications and agents across Next.js, React, Svelte, Vue, and Node.js. - [Vercel CLI](https://positronick.com/listings/vercel-cli): cli — Official command-line interface for deploying and managing Vercel projects, env vars, domains, logs, and deployments from the terminal. - [skills](https://positronick.com/listings/skills): cli — Open agent-skills CLI to install and manage reusable skill packages across Claude Code, Cursor, Codex, OpenCode, and 60+ coding agents. - [Cloudflare Skills](https://positronick.com/listings/cloudflare-skills): plugin — Official collection of Agent Skills, slash commands, and bundled MCP servers that teach coding agents (Claude Code, Cursor, Codex, etc.) how to build on Cloudflare. - [Canvas Design](https://positronick.com/listings/canvas-design): skill — Create beautiful static visual art as .png and .pdf — posters, designs, and artwork — guided by a design philosophy. - [Doc Co-authoring](https://positronick.com/listings/doc-coauthoring): skill — Guide a structured workflow for co-authoring documentation, proposals, technical specs, and decision docs through iterative refinement. - [DOCX (Word)](https://positronick.com/listings/docx): skill — Create, read, edit, and manipulate Word (.docx) documents, including tables of contents, headings, and professional formatting. - [Internal Comms](https://positronick.com/listings/internal-comms): skill — Write internal communications — status reports, leadership updates, newsletters — in the formats a company prefers. - [PDF](https://positronick.com/listings/pdf): skill — Work with PDF files: extract text and tables, merge and split, rotate, watermark, fill forms, encrypt, and create new PDFs. - [Skill Creator](https://positronick.com/listings/skill-creator): skill — Create, modify, and improve Agent Skills, and measure their performance with evals, benchmarks, and variance analysis. - [mcp-to-ai-sdk](https://positronick.com/listings/mcp-to-ai-sdk): cli — CLI that generates versioned, code-owned AI SDK tool stubs from any MCP server to cut token cost and reduce prompt-injection risk. - [Codex plugin for Claude Code (marketplace: openai-codex, plugin: codex)](https://positronick.com/listings/codex-plugin-for-claude-code-marketplace-openai-codex): plugin — Claude Code plugin that lets you run Codex from within Claude Code to review code or delegate background tasks using your local Codex auth. - [Web Artifacts Builder](https://positronick.com/listings/web-artifacts-builder): skill — Build elaborate multi-component claude.ai HTML artifacts with React, Tailwind CSS, and shadcn/ui — for artifacts needing state, routing, or components. - [text-to-lottie](https://positronick.com/listings/text-to-lottie): skill — An agent skill that authors Lottie (Bodymovin) JSON animations rendered live in an official Skia/Skottie player — for creating, editing, or fixing animations with coding agents. - [ml-intern](https://positronick.com/listings/ml-intern): agent — An open-source ML engineer agent that reads papers, trains models, and ships them, routing tool calls across the Hugging Face Hub, Jobs, and sandboxed execution. - [Azure Cost](https://positronick.com/listings/azure-cost): skill — Azure cost management — query and forecast spending, find orphaned resources, and optimize to reduce waste. - [Azure Deploy](https://positronick.com/listings/azure-deploy): skill — Execute Azure deployments for already-prepared apps with existing deployment plans and infrastructure files. - [Azure Storage](https://positronick.com/listings/azure-storage): skill — Work with Azure Storage — Blob, File, Queue, Table, and Data Lake — including access-tier guidance (hot/cool/cold/archive). - [Gemini CLI](https://positronick.com/listings/gemini-cli): harness — Open-source AI agent that brings Gemini directly into your terminal, using a ReAct loop with built-in tools and MCP server support. - [Microsoft Foundry](https://positronick.com/listings/microsoft-foundry): skill — Deploy, evaluate, fine-tune, and manage Microsoft Foundry agents end-to-end — builds, hosted agents, batch/continuous eval, and prompt optimization. - [Stripe CLI](https://positronick.com/listings/stripe-cli): cli — Official command-line tool to build, test, and manage a Stripe integration — trigger and forward webhooks, tail API logs, and CRUD API objects from the terminal. - [v0-sdk](https://positronick.com/listings/v0-sdk): cli — Official TypeScript SDK for the v0 Platform API to programmatically create AI-generated chats, projects, and deployments; ships with a create-v0-sdk-app scaffolder. - [Composition Patterns](https://positronick.com/listings/vercel-composition-patterns): skill — React composition patterns that scale — use when refactoring components toward more composable, maintainable structures. - [Deploy to Vercel](https://positronick.com/listings/deploy-to-vercel): skill — Deploy applications and websites to Vercel — production or preview deployments — straight from a coding agent. - [Vercel CLI with Tokens](https://positronick.com/listings/vercel-cli-with-tokens): skill — Deploy and manage Vercel projects with token-based (non-interactive) auth — deploys, setup, and environment variables via the Vercel CLI. - [LeRobot](https://positronick.com/listings/lerobot): cli — End-to-end robotics toolkit with CLI commands (`lerobot-train`, `lerobot-eval`, `lerobot-info`) for training, evaluating, and running real-world robot policies on PyTorch. - [React Native Skills](https://positronick.com/listings/vercel-react-native-skills): skill — React Native and Expo best practices for building performant mobile apps with coding agents. - [Vercel Optimize](https://positronick.com/listings/vercel-optimize): skill — Vercel cost and performance optimization for deployed Next.js, SvelteKit, Nuxt, and Astro apps — metric-backed, evidence-first recommendations. - [Web Design Guidelines](https://positronick.com/listings/web-design-guidelines): skill — Review UI code for Web Interface Guidelines compliance — accessibility, UX, and design best-practice audits. - [xmcp](https://positronick.com/listings/xmcp): mcp — A local MCP server that turns the X API's OpenAPI spec into callable tools (streaming and webhook routes excluded), served over HTTP at /mcp. - [xurl](https://positronick.com/listings/xurl): cli — A curl-like CLI for the X API that handles OAuth 1.0a and OAuth 2.0 (PKCE, multi-account) and supports streaming, media uploads, and webhooks. - [Claude API](https://positronick.com/listings/claude-api): skill — Reference for building with the Claude API / Anthropic SDK: models, params, streaming, tool use, MCP, caching, and token counting. - [Claude Code](https://positronick.com/listings/claude-code): harness — Agentic coding tool that lives in your terminal, understands your codebase, and executes routine tasks, explains code, and handles git workflows via natural language. - [Claude Agent SDK (TypeScript)](https://positronick.com/listings/claude-agent-sdk-typescript): agent — TypeScript framework for building custom AI agents powered by Claude Code, supporting one-off queries, interactive client sessions, custom tools, and hooks. - [claude-plugins-official](https://positronick.com/listings/claude-plugins-official): plugin — Anthropic-managed directory of high-quality Claude Code plugins, including internal Anthropic plugins and vetted third-party submissions, that extend Claude Code with commands, agents, and MCP servers. - [Claude Platform CLI (ant)](https://positronick.com/listings/claude-platform-cli-ant): cli — Official Go-based CLI for the Claude Developer Platform / Claude API, distinct from the agentic Claude Code tool. - [Brand Guidelines](https://positronick.com/listings/brand-guidelines): skill — Apply Anthropic's official brand colors and typography to any artifact that benefits from a consistent company look-and-feel. - [MCP Builder](https://positronick.com/listings/mcp-builder): skill — Guide for building high-quality MCP servers in Python (FastMCP) or Node/TypeScript (MCP SDK) to integrate external APIs and services. - [PPTX (PowerPoint)](https://positronick.com/listings/pptx): skill — Create, read, and edit PowerPoint (.pptx) decks — slide decks, pitch decks, and presentations — or extract their content. - [Theme Factory](https://positronick.com/listings/theme-factory): skill — Style artifacts — slides, docs, HTML landing pages — with one of 10 preset themes or a theme generated on the fly. - [Webapp Testing](https://positronick.com/listings/webapp-testing): skill — Interact with and test local web apps via Playwright: verify frontend behavior, debug UI, capture screenshots, and view browser logs. - [Strands Agents SDK](https://positronick.com/listings/strands-agents-sdk): agent — An AWS-built, model-driven open-source SDK for building and running AI agents in a few lines of code, used in production by Kiro, Amazon Q, and AWS Glue. - [Kiro CLI](https://positronick.com/listings/kiro-cli): harness — AWS's agentic command-line tool for building software through natural-language chat in your terminal, the successor to the Amazon Q Developer CLI. - [create-cloudflare (C3)](https://positronick.com/listings/create-cloudflare-c3): cli — Official scaffolding CLI that bootstraps and deploys new Workers and framework-based projects using Cloudflare-maintained templates, and installs Wrangler. - [Stripe Agent Toolkit](https://positronick.com/listings/stripe-agent-toolkit): agent — Official Python and TypeScript library that integrates Stripe APIs into agent frameworks (OpenAI Agents SDK, LangChain, CrewAI, Vercel AI SDK) and MCP via function calling. - [Agents SDK (Cloudflare Agents SDK)](https://positronick.com/listings/agents-sdk-cloudflare-agents-sdk): agent — Cloudflare's SDK for building and deploying stateful, persistent AI agents on Workers and Durable Objects, with built-in state, scheduling, WebSockets, MCP, and React hooks. - [Docker Compose](https://positronick.com/listings/docker-compose): cli — Docker CLI plugin to define and run multi-container applications from a single declarative YAML file with one command. - [Docker Scout CLI](https://positronick.com/listings/docker-scout-cli): cli — The 'docker scout' CLI plugin for software supply chain security: generating SBOMs, matching components against vulnerability databases, and evaluating image policy compliance. - [GitHub MCP Server](https://positronick.com/listings/github-mcp-server): mcp — GitHub's official Model Context Protocol server that connects AI agents to GitHub repos, issues, pull requests, and workflows. - [gstack](https://positronick.com/listings/gstack): skill — Garry Tan's exact Claude Code setup — 23 specialist agents and 8 power tools as slash-command skills that turn Claude Code into a virtual engineering team. - [Awesome GitHub Copilot](https://positronick.com/listings/awesome-github-copilot): plugin — GitHub's curated marketplace of custom agents, skills, instructions, hooks, and plugins to extend GitHub Copilot. - [Agent Development Kit (ADK)](https://positronick.com/listings/agent-development-kit-adk): agent — Open-source, code-first toolkit for building, evaluating, and deploying sophisticated multi-agent AI systems, optimized for Gemini but model- and deployment-agnostic. - [Google Cloud CLI (gcloud CLI)](https://positronick.com/listings/google-cloud-cli-gcloud-cli): cli — Official Google Cloud command-line interface (part of the Cloud SDK, including gcloud, gsutil, and bq) for managing Google Cloud resources, AI/Vertex services, and applications. - [Hugging Face MCP Server](https://positronick.com/listings/hugging-face-mcp-server): mcp — Official MCP server that connects MCP-compatible assistants to the Hugging Face Hub for searching models, datasets, Spaces, papers, and docs, plus running Gradio community tools. - [mlintern-plugin](https://positronick.com/listings/mlintern-plugin): plugin — A Claude Code plugin that lets you invoke Hugging Face's ml-intern agent to fine-tune, evaluate, and ship models directly from inside Claude Code. - [zoom-out](https://positronick.com/listings/zoom-out): skill — Get broader, higher-level context on unfamiliar code. - [to-prd](https://positronick.com/listings/to-prd): skill — Turn the current conversation into a PRD on your issue tracker. - [Migration Until Applied](https://positronick.com/listings/migration-until-applied): loop — Run database migrations, fix schema issues, and loop until migrations apply cleanly in dev. - [triage](https://positronick.com/listings/triage): skill — Triage incoming issues through a role-driven state machine. - [grill-with-docs](https://positronick.com/listings/grill-with-docs): skill — Stress-test a plan against your domain model and update the docs inline. - [improve-codebase-architecture](https://positronick.com/listings/improve-codebase-architecture): skill — Find architectural deepening and refactoring opportunities in a codebase. - [prototype](https://positronick.com/listings/prototype): skill — Build a throwaway prototype to flesh out a design before committing. - [setup-matt-pocock-skills](https://positronick.com/listings/setup-matt-pocock-skills): skill — One-time per-repo setup that teaches the engineering skills your conventions. - [tdd](https://positronick.com/listings/tdd): skill — Test-driven development with a strict red-green-refactor loop. - [to-issues](https://positronick.com/listings/to-issues): skill — Break a plan or PRD into independently-grabbable tracker issues. - [write-a-skill](https://positronick.com/listings/write-a-skill): skill — Create new agent skills with proper structure and progressive disclosure. - [Azure MCP Server](https://positronick.com/listings/azure-mcp-server): mcp — MCP server connecting AI agents to 40+ Azure service areas for resource management and queries. - [teach](https://positronick.com/listings/teach): skill — Learn a new skill or concept, grounded in your workspace. - [AutoGen](https://positronick.com/listings/autogen): agent — Programming framework for agentic AI and multi-agent conversation patterns (now in maintenance mode). - [Azure Skills Plugin](https://positronick.com/listings/azure-skills-plugin): plugin — Microsoft's Azure capability plugin: curated Azure skills plus the Azure MCP Server (200+ tools across 40+ services) and Foundry MCP, for real Azure work from coding agents. - [Azure RBAC](https://positronick.com/listings/azure-rbac): skill — Find the least-privilege Azure RBAC role for an identity and generate the CLI commands and Bicep to assign it. - [diagnose](https://positronick.com/listings/diagnose): skill — A disciplined diagnosis loop for hard bugs and performance regressions. - [Microsoft Agent Framework](https://positronick.com/listings/microsoft-agent-framework): agent — Multi-language framework for building production AI agents and multi-agent workflows; successor to Semantic Kernel and AutoGen. - [Skills Catalog for Codex](https://positronick.com/listings/skills-catalog-for-codex): skill — Official catalog of Agent Skills (folders of instructions, scripts, and resources) that Codex and other AI agents can discover and use. - [handoff](https://positronick.com/listings/handoff): skill — Compact the conversation into a handoff document for another agent. - [Notion Skills](https://positronick.com/listings/notion-skills): skill — Official collection of agent skills for working with Notion, including a notion-cli skill for installing and using the ntn CLI via coding agents. - [OpenAI Agents SDK (Python)](https://positronick.com/listings/openai-agents-sdk-python): agent — Lightweight, provider-agnostic framework for building multi-agent workflows with tools, handoffs, guardrails, sessions, and tracing. - [Codex GitHub Action](https://positronick.com/listings/codex-github-action): agent — GitHub Action that runs Codex inside CI/CD workflows to review PRs or apply patches, with configurable sandbox privileges. - [Postgres Language Server](https://positronick.com/listings/postgres-language-server): cli — Official Language Server and CLI toolchain for Postgres, providing autocompletion, type checking, linting, and syntax error detection built on Postgres' own libpg_query parser. - [Azure Kubernetes](https://positronick.com/listings/azure-kubernetes): skill — Plan, create, and configure production-ready Azure Kubernetes Service (AKS) clusters — SKU selection, networking, and security. - [sentry-for-ai](https://positronick.com/listings/sentry-for-ai): plugin — Official Sentry plugin for Claude Code and Cursor that bundles agent skills, the /seer slash command, and auto-configured Sentry MCP to set up Sentry and fix production issues. - [Supabase MCP Server](https://positronick.com/listings/supabase-mcp-server): mcp — Official MCP server that connects AI assistants like Cursor, Claude, and Windsurf to your Supabase projects to manage tables, query data, deploy edge functions, and handle config. - [Hermes](https://positronick.com/listings/hermes): harness — The agent that grows with you — a cross-platform AI agent that installs with one command and bundles its own runtime. - [Stripe MCP Server](https://positronick.com/listings/stripe-mcp-server): mcp — Official Model Context Protocol server exposing Stripe payments, billing, and docs/knowledge-base tools to AI agents, runnable locally via npx or as a hosted remote server at https://mcp.stripe.com. - [Claude Agent SDK for Python](https://positronick.com/listings/claude-agent-sdk-for-python): agent — Python framework for building custom AI agents on top of Claude Code, with query() for one-off tasks and ClaudeSDKClient for interactive sessions, custom tools, and hooks. - [Read Callers Before Write](https://positronick.com/listings/read-callers-before-write): loop — Before editing a symbol, map every caller, re-export, test, and shared util it touches — iterate until the blast radius is fully known, then write. - [Silent Failure Hunt](https://positronick.com/listings/silent-failure-hunt): loop — Hunt down swallowed errors, empty catch blocks, ignored return codes, silent fallbacks, and skipped tests, then make each one fail loud or carry an explicit comment justifying the suppression. - [Algorithmic Art](https://positronick.com/listings/algorithmic-art): skill — Create algorithmic and generative art with p5.js using seeded randomness and interactive parameter exploration — flow fields, particle systems, and more. - [Slack GIF Creator](https://positronick.com/listings/slack-gif-creator): skill — Create animated GIFs optimized for Slack, with constraints, validation tools, and animation concepts. - [XLSX (Excel)](https://positronick.com/listings/xlsx): skill — Open, read, edit, and create spreadsheets (.xlsx, .xlsm, .csv, .tsv) — formulas, formatting, charts, and data cleaning. - [Docker Model Runner CLI](https://positronick.com/listings/docker-model-runner-cli): cli — The 'docker model' CLI plugin for pulling, running, packaging, and serving local LLMs and AI models as OCI artifacts with an OpenAI-compatible API. - [Wrangler](https://positronick.com/listings/wrangler): cli — The official command-line interface for the Cloudflare Developer Platform, used to build, test, configure, and deploy Workers and related services. - [Cloudflare MCP Server (Code Mode)](https://positronick.com/listings/cloudflare-mcp-server-code-mode): mcp — A token-efficient remote MCP server exposing the entire Cloudflare API (~2,500 endpoints) via a Code Mode search/execute pattern at mcp.cloudflare.com. - [GitHub Copilot CLI](https://positronick.com/listings/github-copilot-cli): harness — Brings the Copilot coding agent to the terminal, letting you build, debug, and understand code via natural language. - [rendergit](https://positronick.com/listings/rendergit): cli — A command-line tool that flattens any git repo into a single static HTML page for fast human skimming or for copying the whole codebase into an LLM. - [Symphony](https://positronick.com/listings/symphony): agent — Engineering-preview orchestrator that turns project work into isolated, autonomous Codex implementation runs by monitoring a board and spawning agents. - [Jules Tools](https://positronick.com/listings/jules-tools): harness — Command-line companion and TUI for Jules, Google's asynchronous cloud coding agent, to create and manage agent sessions that write tests, fix bugs, and open pull requests. - [caveman](https://positronick.com/listings/caveman): skill — Ultra-compressed communication mode that cuts token usage ~75%. - [Azure AI](https://positronick.com/listings/azure-ai): skill — Build with Azure AI services — AI Search (vector/hybrid/semantic), Speech, OpenAI, and Document Intelligence (OCR). - [OpenAI Python library (openai)](https://positronick.com/listings/openai-python-library-openai): cli — Official, type-annotated Python client library for the OpenAI REST API, with synchronous and asynchronous clients for the Responses, Chat Completions, and Realtime APIs. - [grill-me](https://positronick.com/listings/grill-me): skill — Get interviewed relentlessly about a plan until it's fully resolved. - [Sentry MCP](https://positronick.com/listings/sentry-mcp): mcp — Official Model Context Protocol server that connects AI coding assistants to Sentry's API for searching issues, retrieving events, and debugging production errors; hosted remotely at mcp.sentry.dev. - [Notion CLI (ntn)](https://positronick.com/listings/notion-cli-ntn): cli — Official command-line tool for developers and coding agents to authenticate, make Notion API requests, upload files, and build/deploy Notion Workers from the terminal. - [Vercel MCP](https://positronick.com/listings/vercel-mcp): mcp — Vercel's official remote MCP server with OAuth, letting AI tools securely search docs and manage Vercel projects, deployments, and logs. - [Supabase Agent Skills](https://positronick.com/listings/supabase-agent-skills): skill — Official Agent Skills that teach AI coding agents (Claude Code, Copilot, Cursor, and 18+ others) how to build correctly on Supabase, covering Database, Auth, Edge Functions, Storage, Realtime, and Postgres best practices. - [OpenClaw](https://positronick.com/listings/openclaw): harness — Your own personal AI assistant for any OS and platform — installs via npm and runs as an always-on gateway daemon. - [sentry-skills](https://positronick.com/listings/sentry-skills): plugin — Open-format Agent Skills used internally by the Sentry team for development, including code review, commit, branch-naming, and security/performance review skills that work across Claude Code, Cursor, Cline, and Copilot. - [Surgical Diff Shrink](https://positronick.com/listings/surgical-diff-shrink): loop — Shrink an over-broad diff back to the minimum that satisfies the goal — every changed line load-bearing, no drive-by edits — re-running tests after each cut. - [Writing Guidelines](https://positronick.com/listings/writing-guidelines): skill — Review docs and prose for Writing Guidelines compliance — voice, tone, and style audits against a writing handbook. - [Ship PR Until Green](https://positronick.com/listings/ship-pr-until-green): loop — Implement on a branch, run tests, push, open a PR, and loop until checks pass and the PR is ready to merge. - [Lint and Typecheck Fix](https://positronick.com/listings/lint-typecheck-fix): loop — Run lint and typecheck, fix reported issues, and loop until the codebase is clean. - [Deploy Verification Loop](https://positronick.com/listings/deploy-verification-loop): loop — On an interval, hit health and smoke endpoints after a deploy until all checks return healthy responses. - [Build Until Green](https://positronick.com/listings/build-until-green): loop — Run the production build, fix compile and bundling errors, and loop until the build succeeds. - [Test Until Green](https://positronick.com/listings/test-until-green): loop — Run your test suite, fix the smallest root cause on failure, and repeat until every test passes. - [Format Until Clean](https://positronick.com/listings/format-until-clean): loop — Run the formatter, fix any remaining style issues, and loop until the codebase formats cleanly with no diffs. - [Spec-First Ship](https://positronick.com/listings/spec-first-ship): loop — Implement from a written spec.md checklist — each iteration completes one unchecked requirement with verification. - [smolagents](https://positronick.com/listings/smolagents): agent — A barebones Python library for building agents that think and act in code, with the `smolagent` and `webagent` CLIs for running multi-step and web-browsing agents. - [Docs Drift Sweep](https://positronick.com/listings/docs-drift-sweep): loop — Treat every operational claim in your docs and runbooks as a hypothesis — verify each against the live system, fix what drifted, and loop until no claim fails verification. - [Autoloop TDD](https://positronick.com/listings/autoloop-tdd): loop — Test-first loop: write a failing test, implement the minimum code to pass, refactor, and repeat. - [Independent Verifier Pass](https://positronick.com/listings/independent-verifier-pass): loop — When implementation claims done, a separate verifier pass runs build, lint, and tests with no access to the implementer's rationale. - [Fix CI Until Green](https://positronick.com/listings/fix-ci-until-green): loop — Fetch the latest failed CI run, reproduce the failure locally, fix it, and repeat until checks pass. - [Coverage Until Threshold](https://positronick.com/listings/coverage-until-threshold): loop — Add focused tests until coverage meets your threshold (e.g. 80%), without changing production behavior unnecessarily. - [Changelog Sync After Ship](https://positronick.com/listings/changelog-sync-after-ship): loop — After shipping a feature, loop until CHANGELOG.md has a user-facing entry and conventional commits are reflected. - [PR Self-Review](https://positronick.com/listings/pr-self-review): loop — Review your own diff like a senior reviewer, fix issues, and repeat for three passes before opening the PR. - [React Best Practices](https://positronick.com/listings/vercel-react-best-practices): skill — React and Next.js performance optimization guidelines from Vercel Engineering, for writing, reviewing, or refactoring components. - [MCP Toolbox for Databases](https://positronick.com/listings/mcp-toolbox-for-databases): mcp — Open-source MCP server (formerly Gen AI Toolbox for Databases) that securely connects AI agents and MCP clients to databases like AlloyDB, Spanner, Cloud SQL, BigQuery, and self-managed Postgres/MySQL. - [Azure Diagnostics](https://positronick.com/listings/azure-diagnostics): skill — Debug Azure production issues with AppLens, Azure Monitor, and resource health — safe triage for App Service, containers, and more. - [AWS CLI](https://positronick.com/listings/aws-cli): cli — The unified command line interface for managing and automating all AWS services from your terminal. - [agent-skills](https://positronick.com/listings/agent-skills-vercel): skill — Vercel's official collection of agent skills for AI coding agents, covering React/Next.js performance, AI SDK usage, web UI guidelines, and Vercel deploys. - [De-Sloppify Pass](https://positronick.com/listings/de-sloppify-pass): loop — After implementation, run a cleanup pass: remove debug code, tighten naming, delete dead branches, and align with project conventions. - [Semantic Kernel](https://positronick.com/listings/semantic-kernel): agent — Model-agnostic SDK for orchestrating, building, and deploying AI agents and multi-agent systems. - [Cloudflare MCP Servers](https://positronick.com/listings/cloudflare-mcp-servers): mcp — A suite of official remote MCP servers (observability, bindings, builds, browser rendering, Radar, AI Gateway, and more) that let MCP clients manage Cloudflare via natural language. - [Smart Commit](https://positronick.com/listings/smart-commit): skill — Cluster uncommitted changes into logical groups and commit each with a clean conventional commit message — plus a Keep-a-Changelog update pass. - [Convention Conformance Sweep](https://positronick.com/listings/convention-conformance-sweep): loop — Align new code to the codebase's own idioms — sample its neighbors, fix one mismatch per pass, and when two patterns conflict pick the more recent or better-tested one rather than averaging them. - [Oh My OpenAgent (omo)](https://positronick.com/listings/oh-my-openagent): harness — A multi-model coding-agent harness that installs into OpenCode and the OpenAI Codex CLI. - [Ship](https://positronick.com/listings/ship): skill — Take a finished change from working tree to a green, mergeable PR — one command chaining simplify, verify, code-review, smart-commit, branch hygiene, PR, and babysit-to-green. - [ECC](https://positronick.com/listings/ecc): skill — A harness-native operator system — skills, instincts, memory, and security — that tunes Claude Code, Codex, OpenCode, and Cursor for research-first development. - [Positronick](https://positronick.com/listings/positronick): skill — Teach your agent the positronick.com registry: find, inspect and install souls and agent tooling through the MCP server or the CLI. - [Ralph Loop](https://positronick.com/listings/ralph-loop): loop — Repeatedly relaunch a fresh coding-agent session against a prompt until the implementation plan is complete. - [Verify or Drop](https://positronick.com/listings/verify-or-drop): loop — For every candidate item in a catalog or dataset, independently re-verify the claim and mechanically confirm its source URL resolves — include it with evidence or drop it with a written reason. - [Merge to Live Parity](https://positronick.com/listings/merge-to-live-parity): loop — After merging, loop until production actually reflects the merge — pipeline green, the new commit serving, fresh routes answering, and schema plus data applied. - [Interview Then Orchestrate](https://positronick.com/listings/interview-then-orchestrate): loop — Before a large batch job, surface the few decisions only the owner can make, lock them in one up-front interview, then run the whole batch unattended — looping on blockers, not on questions. - [Notion plugin for Cursor](https://positronick.com/listings/notion-plugin-for-cursor): plugin — Official Cursor plugin packaging Notion Skills with Notion's hosted MCP server (https://mcp.notion.com/mcp) for one-click workspace access inside Cursor. - [Superpowers](https://positronick.com/listings/superpowers): skill — An agentic skills framework and complete software-development methodology that makes your coding agent plan, spec, and verify before it writes code. - [fic](https://positronick.com/listings/fic-cli): cli — Unofficial CLI for the Fatture in Cloud API v2 — JSON-first, jq-pipeable, agent-friendly. - [Boot and Probe](https://positronick.com/listings/boot-and-probe): loop — Green tests are not a running app — build the production image, boot it against a fresh throwaway database, probe the real routes and contracts, fix, and re-boot until everything answers. - [Checkpoint-Driven Execution](https://positronick.com/listings/checkpoint-driven-execution): loop — Write the success criteria and load-bearing assumptions first, complete exactly one step per pass while restating done / verified / left, and loop until every criterion is checked off and backed by evidence. - [React View Transitions](https://positronick.com/listings/vercel-react-view-transitions): skill — Implement smooth, native-feeling animations with React's View Transition API — page transitions, route animations, and CSS view-transition pseudo-elements. - [Schema Migration Drift to Zero](https://positronick.com/listings/schema-migration-drift-zero): loop — After every schema edit, regenerate migrations and prove there is no drift — loop until a fresh generate produces no new files and leaves the working tree clean. - [Multi-Agent Supervised Coding Loop](https://positronick.com/listings/multi-agent-supervised-coding-loop): loop — A markdown-and-bash protocol that turns a well-scoped repo into a supervised multi-agent coding loop where a Beacon ranks the next work, you approve it, and path-owning agents build in isolated git worktrees. - [MCP Reference Servers](https://positronick.com/listings/mcp-reference-servers): mcp — Curated reference MCP server implementations (Filesystem, Fetch, Git, Memory, Sequential Thinking, Everything) maintained by the Anthropic-managed Model Context Protocol project to demonstrate MCP features and SDK usage. - [Decisive Pick Loop](https://positronick.com/listings/decisive-pick-loop): loop — Collapse a menu of options into one committed recommendation — research each candidate with real evidence instead of priors, score against explicit criteria, and don't stop until a single pick stands with a named runner-up. - [Store-Content Parity](https://positronick.com/listings/store-content-parity): loop — When your sync pipeline only upserts, removals never propagate — loop until the live store's rows exactly match the curated source files, pruning orphans deliberately. - [Zero-Warnings Quality Gauntlet](https://positronick.com/listings/zero-warnings-gauntlet): loop — Run lint, typecheck, tests, and build as one chained gauntlet under a 'a warning FAILS' bar, and loop until the whole chain exits clean with the word 'warning' nowhere in its output. - [Red-Team Your Own Feature](https://positronick.com/listings/self-red-team): loop — Attack your own just-built feature's trust assumptions — spoofable identifiers, client-settable fields, lookalike handles, reclamation attacks — fix each break and re-attack until every attack fails. - [Agent Loop (Issues to PRs)](https://positronick.com/listings/agent-loop-issues-to-prs): loop — A Ralph-style loop that turns open GitHub issues into pull requests, one task per iteration, until none remain. - [Session Distill](https://positronick.com/listings/session-distill): loop — After significant work, distill the non-obvious lessons — gotchas, environment quirks, corrections you received — into durable notes, looping until a fresh review pass surfaces nothing unrecorded. - [Sentry CLI (sentry)](https://positronick.com/listings/sentry-cli-sentry): cli — The newer TypeScript Sentry CLI built for developers and AI agents, with Seer-powered root cause analysis (sentry issue explain/plan), DSN auto-detection, and JSON output. - [Ship Kit](https://positronick.com/listings/ship-kit): plugin — A Claude Code plugin that takes a finished change from working tree to a green, mergeable PR, then drives the review loop to a fresh approval. - [Intent-Test Mutation Guard](https://positronick.com/listings/intent-test-mutation-guard): loop — Mutate your own production code on purpose, prove a test fails for each change, and loop until no surviving mutant slips past the suite. ## Profiles - [GitHub](https://positronick.com/profiles/github): organization, verified - [Google](https://positronick.com/profiles/google): organization, verified - [Hugging Face](https://positronick.com/profiles/huggingface): organization, verified - [Andrej Karpathy](https://positronick.com/profiles/karpathy): person, verified - [Matt Pocock](https://positronick.com/profiles/mattpocock): person, verified - [Microsoft](https://positronick.com/profiles/microsoft): organization, verified - [Notion](https://positronick.com/profiles/notion): organization, verified - [Nicholas Sollazzo](https://positronick.com/profiles/nsollazzo): person, verified - [Jesse Vincent](https://positronick.com/profiles/obra): person, verified - [OpenAI](https://positronick.com/profiles/openai): organization, verified - [Sentry](https://positronick.com/profiles/sentry): organization, verified - [Stripe](https://positronick.com/profiles/stripe): organization, verified - [Vercel](https://positronick.com/profiles/vercel): organization, verified - [X Developer Platform](https://positronick.com/profiles/xdevplatform): organization, verified - [Affaan Mustafa](https://positronick.com/profiles/affaan-m): person, verified - [Anthropic](https://positronick.com/profiles/anthropic): organization, verified - [Amazon Web Services](https://positronick.com/profiles/aws): organization, verified - [Diffusion Studio](https://positronick.com/profiles/diffusionstudio): organization, verified - [Docker](https://positronick.com/profiles/docker): organization, verified - [Garry Tan](https://positronick.com/profiles/garrytan): person, verified - [Earendil Works](https://positronick.com/profiles/earendil-works): organization, verified - [Cloudflare](https://positronick.com/profiles/cloudflare): organization, verified - [YeonGyu-Kim](https://positronick.com/profiles/code-yeongyu): person, verified - [shadcn](https://positronick.com/profiles/shadcn): person - [Geoffrey Huntley](https://positronick.com/profiles/ghuntley): person, verified - [loops!](https://positronick.com/profiles/loops): organization, verified - [Nous Research](https://positronick.com/profiles/nousresearch): organization, verified - [OpenClaw](https://positronick.com/profiles/openclaw): organization, verified - [Positronick](https://positronick.com/profiles/positronick): organization, official - [Supabase](https://positronick.com/profiles/supabase): organization, verified - [Anshuli Gupta](https://positronick.com/profiles/anshulixyz): person, verified - [Ben Tossell](https://positronick.com/profiles/bentossell): person, verified ## Blog - [openclaw 2026.6.10](https://positronick.com/blog/openclaw-v2026-6-10): release — Automatic fast mode for talks: OpenClaw can enable fast mode for short conversational turns, then return to normal mode for longer runs with bounded fallback and delivery behavior. (#85104) Thanks… — raw: https://positronick.com/api/blog/openclaw-v2026-6-10.md - [openclaw 2026.6.9](https://positronick.com/blog/openclaw-v2026-6-9): release — Richer Telegram delivery: Telegram now sends rich HTML, preserves rich markdown and sticker paths, renders progress drafts and command output more faithfully, normalizes HTML tables safely, and keeps… — raw: https://positronick.com/api/blog/openclaw-v2026-6-9.md - [Hermes Agent v0.17.0 (v2026.6.19)](https://positronick.com/blog/hermes-v2026-6-19): release — Release Date: June 19, 2026 Since v0.16.0: ~1,475 commits · ~800 merged PRs · 1,693 files changed · 235,390 insertions · 50,730 deletions · 300+ issues closed · 245 community contributors The Reach… — raw: https://positronick.com/api/blog/hermes-v2026-6-19.md - [openclaw 2026.6.8](https://positronick.com/blog/openclaw-v2026-6-8): release — Richer channel delivery: Telegram and WhatsApp are less brittle: Telegram renders structured text with tables, lists, expandable blockquotes, preserved intentional line breaks, and CLI-backed… — raw: https://positronick.com/api/blog/openclaw-v2026-6-8.md - [Positronick CLI v0.1.2](https://positronick.com/blog/positronick-cli-v0-1-2): release — agent-usage skill + MCP server instructions (#19) package manager distribution (Homebrew, npm, Scoop, Winget, AUR) (#16) positronick profile create + list (admin) (#21) add Hermes integration guide… — raw: https://positronick.com/api/blog/positronick-cli-v0-1-2.md - [ship-kit v1.0.0](https://positronick.com/blog/ship-kit-ship-kit-v1-0-0): release — First release of ship-kit — the ship → babysit Claude Code plugin. /ship — take a working tree to a green, mergeable PR (simplify → verify → code-review → smart-commit → branch hygiene → PR → babysit… — raw: https://positronick.com/api/blog/ship-kit-ship-kit-v1-0-0.md - [openclaw 2026.6.6](https://positronick.com/blog/openclaw-v2026-6-6): release — Tighter security boundaries: transcript, sandbox, MCP, browser, channel, and exec-approval paths now fail closed around unsafe access, timed-out approvals, and malformed boundary input. (#91529,… — raw: https://positronick.com/api/blog/openclaw-v2026-6-6.md - [Positronick CLI v0.1.1](https://positronick.com/blog/positronick-cli-v0-1-1): release — poll survives HTTP 429 — back off, honor Retry-After, keep polling (#15) — raw: https://positronick.com/api/blog/positronick-cli-v0-1-1.md - [Positronick CLI v0.1.0](https://positronick.com/blog/positronick-cli-v0-1-0): release — API client, config resolution, and fuzzy search (#1) (Nicholas Sollazzo ) auth — device-flow login, API keys, credential store (#4) (Nicholas Sollazzo ) hidden admin commands — soul/listing create +… — raw: https://positronick.com/api/blog/positronick-cli-v0-1-0.md - [openclaw 2026.6.5](https://positronick.com/blog/openclaw-v2026-6-5): release — Safer channel output: QQBot strips model reasoning and thinking scaffolding before native delivery, so users see the final answer rather than raw internal markup. (#89913, #90132) Thanks @openperf,… — raw: https://positronick.com/api/blog/openclaw-v2026-6-5.md - [Hermes Agent v0.16.0 (2026.6.5) — The Surface Release](https://positronick.com/blog/hermes-v2026-6-5): release — Release Date: June 5, 2026 Since v0.15.2: 874 commits · 542 merged PRs · 1,962 files changed · 205,216 insertions · 46,217 deletions · 399 issues closed (2 P0, 62 P1, 16 security-tagged) · 170… — raw: https://positronick.com/api/blog/hermes-v2026-6-5.md - [openclaw 2026.6.1](https://positronick.com/blog/openclaw-v2026-6-1): release — Resilient agent and Codex runs: interrupted tool calls, stale session bindings, compaction handoffs, auth-profile failover, reasoning-tag cleanup, yielded subagents, and generated-media delivery all… — raw: https://positronick.com/api/blog/openclaw-v2026-6-1.md - [openclaw 2026.5.28](https://positronick.com/blog/openclaw-v2026-5-28): release — Agent and Codex runtime recovery is steadier: subagents keep cwd/workspace separation, hook context stays prompt-local, session locks release on timeout abort while live OpenClaw locks survive… — raw: https://positronick.com/api/blog/openclaw-v2026-5-28.md - [Hermes Agent v0.15.2 (2026.5.29.2)](https://positronick.com/blog/hermes-v2026-5-29-2): release — Release Date: May 29, 2026 Packaging): ship bundled plugin.yaml manifests in wheel and sdist (827f7f07) Thank you to everyone who contributed to this release! @outsourc-e (1 commit) @dparikh79 (1… — raw: https://positronick.com/api/blog/hermes-v2026-5-29-2.md - [Hermes Agent v0.15.1 (2026.5.29) — The Patch Release](https://positronick.com/blog/hermes-v2026-5-29): release — Release Date: May 29, 2026 Since v0.15.0: 28 commits · 21 merged PRs · hotfix release · 9 contributors The Patch Release. A same-day hotfix for v0.15.0. Headline fix: the dashboard infinite-reload… — raw: https://positronick.com/api/blog/hermes-v2026-5-29.md - [Hermes Agent v0.15.0 (2026.5.28) — The Velocity Release](https://positronick.com/blog/hermes-v2026-5-28): release — Release Date: May 28, 2026 Since v0.14.0: 1,302 commits · 747 merged PRs · 1,746 files changed · 282,712 insertions · 36,699 deletions · 560+ issues closed (15 P0, 65 P1, 19 security-tagged) · 321… — raw: https://positronick.com/api/blog/hermes-v2026-5-28.md - [Hermes Agent v0.14.0 (2026.5.16)](https://positronick.com/blog/hermes-v2026-5-16): release — Release Date: May 16, 2026 Since v0.13.0: 808 commits · 633 merged PRs · 1393 files changed · 165,061 insertions · 545 issues closed (12 P0, 50 P1) · 215 community contributors (including co-authors)… — raw: https://positronick.com/api/blog/hermes-v2026-5-16.md - [Hermes Agent v0.13.0 (2026.5.7) — The Tenacity Release](https://positronick.com/blog/hermes-v2026-5-7): release — Release Date: May 7, 2026 Since v0.12.0: 864 commits · 588 merged PRs · 829 files changed · 128,366 insertions · 282 issues closed (13 P0, 36 P1) · 295 community contributors (including co-authors)… — raw: https://positronick.com/api/blog/hermes-v2026-5-7.md - [Hermes Agent v0.12.0 (2026.4.30)](https://positronick.com/blog/hermes-v2026-4-30): release — Release Date: April 30, 2026 Since v0.11.0: 1,096 commits · 550 merged PRs · 1,270 files changed · 217,776 insertions · 213 community contributors (including co-authors) The Curator release — Hermes… — raw: https://positronick.com/api/blog/hermes-v2026-4-30.md - [Hermes Agent v0.11.0 (2026.4.23)](https://positronick.com/blog/hermes-v2026-4-23): release — Release Date: April 23, 2026 Since v0.9.0: 1,556 commits · 761 merged PRs · 1,314 files changed · 224,174 insertions · 29 community contributors (290 including co-authors) The Interface release — a… — raw: https://positronick.com/api/blog/hermes-v2026-4-23.md - [Hermes Agent v0.10.0 (2026.4.16)](https://positronick.com/blog/hermes-v2026-4-16): release — Release Date: April 16, 2026 The Tool Gateway release — paid Nous Portal subscribers can now use web search, image generation, text-to-speech, and browser automation through their existing… — raw: https://positronick.com/api/blog/hermes-v2026-4-16.md - [Hermes Agent v0.9.0 (v2026.4.13)](https://positronick.com/blog/hermes-v2026-4-13): release — Release Date: April 13, 2026 Since v0.8.0: 487 commits · 269 merged PRs · 167 resolved issues · 493 files changed · 63,281 insertions · 24 contributors The everywhere release — Hermes goes mobile… — raw: https://positronick.com/api/blog/hermes-v2026-4-13.md - [Hermes Agent v0.8.0 (v2026.4.8)](https://positronick.com/blog/hermes-v2026-4-8): release — Release Date: April 8, 2026 The intelligence release — background task auto-notifications, free MiMo v2 Pro on Nous Portal, live model switching across all platforms, self-optimized GPT/Codex… — raw: https://positronick.com/api/blog/hermes-v2026-4-8.md - [Hermes Agent v0.7.0 (v2026.4.3)](https://positronick.com/blog/hermes-v2026-4-3): release — Release Date: April 3, 2026 The resilience release — pluggable memory providers, credential pool rotation, Camofox anti-detection browser, inline diff previews, gateway hardening across race… — raw: https://positronick.com/api/blog/hermes-v2026-4-3.md - [Hermes Agent v0.6.0 (v2026.3.30)](https://positronick.com/blog/hermes-v2026-3-30): release — Release Date: March 30, 2026 The multi-instance release — Profiles for running isolated agent instances, MCP server mode, Docker container, fallback provider chains, two new messaging platforms… — raw: https://positronick.com/api/blog/hermes-v2026-3-30.md - [Hermes Agent v0.5.0 (v2026.3.28)](https://positronick.com/blog/hermes-v2026-3-28): release — Release Date: March 28, 2026 The hardening release — Hugging Face provider, /model command overhaul, Telegram Private Chat Topics, native Modal SDK, plugin lifecycle hooks, tool-use enforcement for… — raw: https://positronick.com/api/blog/hermes-v2026-3-28.md - [Hermes Agent v0.4.0 (v2026.3.23)](https://positronick.com/blog/hermes-v2026-3-23): release — Release Date: March 23, 2026 The platform expansion release — OpenAI-compatible API server, 6 new messaging adapters, 4 new inference providers, MCP server management with OAuth 2.1, @ context… — raw: https://positronick.com/api/blog/hermes-v2026-3-23.md - [Hermes Agent v0.3.0 (v2026.3.17)](https://positronick.com/blog/hermes-v2026-3-17): release — Release Date: March 17, 2026 The streaming, plugins, and provider release — unified real-time token delivery, first-class plugin architecture, rebuilt provider system with Vercel AI Gateway, native… — raw: https://positronick.com/api/blog/hermes-v2026-3-17.md - [Hermes Agent v0.2.0 (2026.3.12)](https://positronick.com/blog/hermes-v2026-3-12): release — Release Date: March 12, 2026 First tagged release since v0.1.0 (the initial pre-public foundation). In just over two weeks, Hermes Agent went from a small internal project to a full-featured AI agent… — raw: https://positronick.com/api/blog/hermes-v2026-3-12.md ## API - [Souls JSON API](https://positronick.com/api/souls): machine-readable list of every soul - [Soul detail JSON](https://positronick.com/api/souls/): metadata + body for one soul - [Raw SOUL.md endpoint](https://positronick.com/api/souls/.md): the verbatim installable body - [Listings JSON API](https://positronick.com/api/listings): the registry — filter with ?type=harness|cli|mcp|agent|skill|plugin|loop - [Blog JSON API](https://positronick.com/api/blog): machine-readable posts — filter with ?kind=article|release|link - [Research API](https://positronick.com/api/research): what's new — ?since= returns newer posts + a "latest" high-water mark so agents poll only the delta and avoid stale info ## Optional - [Sitemap](https://positronick.com/sitemap.xml) - [Blog RSS feed](https://positronick.com/blog/feed.xml)