Autonomous AI agents that perform tasks independently
Matteo Leonesi
Claim Memory Graph: a lightweight memory layer for inspectable LLM judge and reviewer decisions.
isnoobgrammer
15 composable skills for AI coding agents — install via npx
dimon94
Standalone AI agent skill for brainstorming without specs, plans, commits, scaffolding, or implementation.
john-mg
Local-runtime spend caps and capability-gated model routing for AI agents. Prompts, API keys, and signing keys stay inside the customer runtime. Zero data plane involvement.
...moreHao Peng
A framework-agnostic evidence gate for LLM agent claims.
jonrhaider
A minimalist LLM framework for building AI agents and workflows with JSON configuration
karl4th
Terminal AI agent for code operations via Moonshot or DeepSeek API
A magnifying glass for your AI agent — open-source forensics + interpretability for LLM agents.
Ido Koren
Multi-agent orchestration framework with a live web dashboard (placeholder)
GitHub Actions
Financial trading & investing agent
wangshiqi308
Rounds — AI does rounds on your production. Self-hosted AI SRE: investigate, dashboard, alert, remediate.
AgentForge contributors
Runtime library for projects scaffolded by AgentForge. Provides base classes, the LLM provider factory, and shared utilities.
...moreMahika Jadhav
Web intelligence that only thinks when the web changes. Bright Data + LLM agent cache — zero tokens on unchanged pages.
AI code/PR review agent. Fetches a pull request, asks an LLM to review it, posts inline comments + summary verdict back to the VCS. Self-hosted, multi-VCS (GitHub, GitLab, Bitbucket, Azure DevOps), multi-LLM (Anthropic / OpenAI / Google / Claude Code / Ollama). Standalone: no inter-package runtime deps.
...moreAutoCode
Autonomous AI coding agent CLI — like Claude Code, works with any OpenAI-compatible API
Production-to-dev bridge. Ingests logs/errors from observability tools, clusters them, asks an LLM to summarize each cluster, opens or updates issues on GitHub/GitLab. Optional handoff to relay-agent closes the full SDLC loop. Standalone: no inter-package runtime deps.
...moreAr9av
A skill-based framework for building and maintaining an AI-maintained Obsidian knowledge base (Karpathy's LLM Wiki pattern) across any AI coding agent.
...moreCodeWarrior4Life
Lattice Cortex -- compile-don't-retrieve knowledge layer + agent-session runtime + cost-aware LLM routing
Independent AI peer review of git diffs for Claude Code and other coding agents
LangChain integration for TinyFish Web Agent - AI-powered web automation
vuejs-ai
The Vue framework for terminal UIs. SFC & JSX, Yoga flexbox, HMR, and testing out of the box.
camtrik
Local dashboard for Claude Code, Codex, OpenCode, OpenClaw and Qoder session history, token usage, cost tracking, tool calls and subagent replay.
...moremr-gl00m
Local-first agentic framework. We built it butter. 🧈
shawnq-msft
Chinese MCP server example for Dianping local service search and AI agent tool calling.