Autonomous AI agents that perform tasks independently
amazadfar
Async-first Python runtime for building provider-agnostic LLM, agent, tool-calling, streaming, caching, and structured-output workflows across OpenAI, Anthropic, and Google Gemini.
...moregokborayilmaz
An AI-powered automated benchmark team designed to dynamically generate accurate dataset test-suites and automatically evaluate multiple LLM models (GPT-4.1, GPT-4o, GPT-4o-mini) simultaneously.
...morejiuguandemao
Multimodal AI testing agent for Web apps: Qwen-VL screenshot/video analysis, DeepSeek review, bug localization, log/code analysis, and pytest/Playwright test generation.
...moresharakusatoh
Windows desktop operator powered by Codex App Server
Aditya-Khadye
MCP server + LangGraph agent for analyzing FDA-style clinical trial protocols. Exposes 4 tools to Claude Code for entity extraction, adverse-event clustering, and summarization. FastAPI, Pandas ETL, AWS-ready Docker.
...moreDannyBruno
Static + runtime linter for LLM agent prompts, skills, and tool definitions. Model-aware policy for Claude, GPT, OpenRouter.
...moreLightweight Agent Contributors
A lightweight LLM agent framework supporting async OpenAI and Anthropic APIs with ReAct agents, TODO-based agents, and built-in tools
...morePortable task-to-code pipeline that works with any LLM. Turn a one-line task into a verified code change — diff + test + verify loop. +54 pts on a 156-check benchmark vs raw prompting.
...morePostgreSQL storage backend plugin for the Orchid AI framework
ChromaDB vector-backend plugin for the Orchid AI framework
Docxodus contributors
Anchor-addressed DOCX editing for LLM agents — a thin client over Docxodus' DocxSession.
FortifyOS runtime protection for LangChain and LangGraph agents — zero code changes required.
Multi-provider LLM agent with an interactive REPL
hlmmkttm
Repo-specific drift monitoring for AI-agent runs.
GitHub Actions
Template repository for custom AI agent skills with a multi-platform terminal installer (Cursor, Claude Code, Codex, OpenCode, Pi).
...morejorgedavidixc
CLI to install AI agents, skills, and CLAUDE.md files across a multi-project workspace
GitHub Actions
A Pi extension that turns high-level objectives into phased, multi-session construction plans with dependency tracking and verification gates.
...moreComputer Use Cloud — a managed cloud sandbox with a browser and a desktop, driven by your choice of LLM. Preview release.
...morekrewe
LangChain.js bindings for the krewe pay-per-call AI inference network. Exposes Embeddings, an LLM, and Tools backed by /v2/predict on Base. Settles each call in USDC via x402 — no API keys.
...moreAntigravity
Persistent memory for LLM agents
coseto6125
EgentCodePlexus (ecp) — symbol-level code intelligence graph for AI agents and LLMs
yongjiexue
Make coding agents stronger engineering partners for reviews, implementation planning, and system design.
sedlukha
Sync .agents/ (single source of truth) into .claude/ and .github/ so Claude Code and GitHub Copilot pick up the same agent and skill definitions.
...morecode2mp4
KDNA CLI — create, validate, install, and manage domain cognition packages for AI agents.