The reliability layer for LLM tool calls. Intercepts every call, validates arguments against your schema, auto-repairs hallucinated args.
GitHub repository with 5 stars and 0 forks.
Language: Python
Topics: agents, anthropic, function-calling, llm, mcp, openai, python, reliability, schema-validation, tool-calling
Trending score 0.05, freshness score 0.00, stars gained +0, forks gained +0.
2026-06-15: 5 stars and 0 forks.
The daily arena where AI agents clash to rank tomorrow’s S&P 500 winners and losers. Their only judge is the future — the one truth that simply cannot be cheated.
GitHub repository with 14 stars and 7 forks.
Trending score: 0.07; stars gained: +0; forks gained: +0.
Language: Python
Topics: agents, ai, anthropic-claude, benchmark, chatgpt, gemini-cli
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
GitHub repository with 198 stars and 46 forks.
Trending score: 2.78; stars gained: +22; forks gained: +3.
Language: Python
Topics: agent, agent-harness, agentic, ai, chatgpt, claude
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
GitHub repository with 28,762 stars and 1,947 forks.
Trending score: 6.47; stars gained: +2,586; forks gained: +205.
Language: Python
Topics: agent, ai, anthropic, claude-code, compression, context-engineering
The agent that grows with you
GitHub repository with 194,452 stars and 34,097 forks.
Trending score: 6.00; stars gained: +932; forks gained: +246.
Language: Python
Topics: ai, ai-agent, ai-agents, anthropic, chatgpt, claude
Self-hosted AI workspace.
GitHub repository with 71,772 stars and 9,165 forks.
Trending score: 5.92; stars gained: +800; forks gained: +131.
Language: Python
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.
GitHub repository with 6,353 stars and 465 forks.
Trending score: 5.86; stars gained: +1,240; forks gained: +69.
Language: Python
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
GitHub repository with 66,674 stars and 10,853 forks.
Trending score: 5.60; stars gained: +1,461; forks gained: +228.
Language: Python
Learn it. Build it. Ship it for others.
GitHub repository with 33,044 stars and 5,407 forks.
Trending score: 5.59; stars gained: +743; forks gained: +108.
Language: Python
Topics: agents, ai, ai-agents, ai-engineering, computer-vision, course
ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.
GitHub repository with 819 stars and 42 forks.
Trending score: 1.61; stars gained: +5; forks gained: +1.
Language: TypeScript
Topics: adhd, agents, ai, ai-agents, brainstorm, chain-of-thought
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
GitHub repository with 1,958 stars and 169 forks.
Trending score: 2.20; stars gained: +6; forks gained: +2.
Topics: agent-skills, agentic-workflows, ai-agents, codex, mcp, prompt-engineering
A menu bar app that can become anything you ask it to be.
GitHub repository with 54 stars and 1 forks.
Trending score: 0.51; stars gained: +0; forks gained: +0.
Language: TypeScript
Topics: agents, agi, ai
Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.
GitHub repository with 55 stars and 6 forks.
Trending score: 0.85; stars gained: +1; forks gained: +0.
Language: Rust
Topics: agent, agents, ai, ai-agents, browser-automation, claude-code
Static analyzer for agent reliability.
GitHub repository with 19 stars and 4 forks.
Trending score: 0.33; stars gained: +0; forks gained: +0.
Language: Go
Topics: agent-security, agent-security-eval, agent-security-scanner, agent-security-tools, agent-tools, agents
Entity intelligence workspace for public research, sourced dossiers, Convex runtime state, MCP tools, and agent context packs.
GitHub repository with 14 stars and 3 forks.
Trending score: 0.00.
Language: TypeScript