AI Agents & Frameworks
Autonomous agents and the frameworks to build them — orchestration, planning, multi-agent systems. Tracked daily with star velocity from real snapshots.
The definitive OpenAI, Claude, MCP, Harness, Evals, and Production Agent Systems learning roadmap.
A verification layer for scientific work
An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, and a browser UI, while you keep your hand on every permission.
Independently installable Pi Coding Agent extensions for AI coding workflows: LSP diagnostics/code actions for TypeScript, JavaScript, Python and more, Chrome DevTools automation, Firecrawl web scraping, Google GenAI/Gemini grounding, Codex tools, statuslines, subagents, and S3/R2 sync.
Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.
Durable MCP control plane for long-running Codex Desktop tasks
Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacement for grep/cat/read/ls in Claude Code, Codex, Cursor, Aider, OpenHands.
Self-hosted AI SRE for Kubernetes — zero-instrumentation eBPF observability plus a copilot that fixes issues through guardrailed, self-verifying actions. BYO-LLM, air-gapped capable.
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
Stop re-explaining your data to your AI every session. The individual-analyst context layer, delivered over MCP (Claude Code / Cursor / Codex).
The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on long sessions, while planning, remembering your codebase, and shipping features in parallel from a single self-hosted binary.
🤖 AI Agent-driven Kaggle competition workflow. Battle-tested patterns for score stabilization, submission troubleshooting, kernel workflows, and spec-driven development.
OpenCode goal plugin for Codex-style goal mode, /goal slash commands, persistent objectives, and AI coding agent focus.
Bring Your Own Browser — let your AI agent use the Chrome you already have open
A Simple Baseline for Video World Models with Memory
Reverse-engineering AI assistant for the Web
Live2D 桌面Agent (Electron + TS) — Cyrene from Honkai: Star Rail. Chat, emotional interaction, personalized memory.
BlitzOS allows cloud agents to boot already knowing your work, and keep working with your laptop closed
Official SDK, Claude Code plugin and facilitator docs for r0x, the x402 facilitator for Robinhood Chain.
Code based orchestration for any coding agent.
An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.
Claude Code / OpenClaw skills for Google Maps lead generation. Scrape businesses, extract emails, analyze competitors, write cold outreach — powered by gmapsscraper.io API.
🧠 Hybrid long-term memory plugin for OpenClaw agents — SQLite+FTS5 for structured facts, LanceDB for semantic recall
Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub Copilot, and more) work as teammates in channels, threads, DMs, and shared tasks. Your data stays on your machines.
A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.
Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures which models earn their seat.
QuantClaw is a plug-and-play task-type routing quantization plugin for OpenClaw.
学习Agent开发的笔记，尝试让Agent从可用到可靠
Control your Pi coding agent from your phone. Pair with a one-time QR code and chat with your local agent — even when you're away from your computer.
Local-first AI workspace for macOS. Ten workspaces — Coder, Agent Swarm, Finance, 3D Forge, Sandbox, Virtual OS and more. 12 providers, or fully offline with Ollama. No backend, no telemetry, no account. Your keys and files stay on your machine. 8.9 MB, MIT.