Autonomous AI agents that perform tasks independently
jfk
Cost-free Ollama-powered code-review agent for Claude Code
Project-neutral, multi-agent workflow core: a fixed backbone of steps that drives an issue from backlog to done, customised per project via config + add-only Lego extensions.
...moreAgent-first Python CLI for querying Overture Maps (overturemaps.org) data, built so LLM agents (and humans) can answer geospatial questions without GIS expertise. Forked from overturemaps-py.
...moregoyaljai
Android emulator automation for AI agents and developers. Zero setup — SDK, emulator, and AVD are bootstrapped automatically on first run.
...moresanchitrk
Toolkit for building AI agents and agent harness.
GitHub Actions
OpenCode plugin for creating and managing model variants of agents
GitHub Actions
A dev-time CLI that reflects your live API for AI coding agents — verify what the server actually does, not what the code assumes.
...moreUniversal agent server. Wraps any LangGraph graph and exposes it over standard agent protocols — Vercel AI SDK, Claude Code, TUIs, and more.
...moreA hierarchical multi-agent harness that autonomously audits a codebase, finds high-value improvements, and applies them in TDD-gated iterations.
...morelatchgate-ai
OpenAI Agents SDK integration for LatchGate — execution security kernel for AI agents
latchgate-ai
CrewAI integration for LatchGate — execution security kernel for AI agents
latchgate-ai
LangChain integration for LatchGate — execution security kernel for AI agents
Norman de la Paz-Tabora
Consciousness-Inspired Middleware & Agent for LLMs — Acknowledgement Theory of Consciousness (ATC)
Token-budget-aware graph navigation for AI coding agents. Serve exactly the noodles your LLM needs.
Kedos srl
KeGAL - Kedos Graph Agent for LLM
mathu97
A super simple monitoring system for Claude agents — full session traces as JSON in blob storage.
Three-axis efficiency scoring for Claude Code sessions — token economy, trajectory quality, deterministic waste. Self-hosted; nothing leaves your machine.
...moreUnified LLM evaluation: A/B uplift, Panel/Jury judges, Krippendorff α, Cohen κ, pairwise preference, Elo tournament, and bias detection
...moreSimon Willison
Storage-agnostic file-editing tools (view / str_replace / insert) for Datasette Agent plugins
Lyrenth
Read the web as clean AIDocuments through Lyrenth (with LangChain and LlamaIndex adapters).
LangChain (Python) callback handler that adds RANKIGI cryptographic receipts to every LLM, tool, agent, and retriever step.
...moreAutonomous coding harness over Claude Code + Kagura Memory
An open-source browser sandbox and automation infrastructure for AI agents, with session management, screenshots, PDFs, proxies, and anti-bot tooling. #opensource
...moreAn open-source desktop app to orchestrate multiple AI CLI agents simultaneously with automations and Kanban management. #opensource
...more