Autonomous AI agents that perform tasks independently
HAON <[email protected]>
HAON PowerHub — miner agent: rent out idle GPU time on a decentralized compute marketplace.
Fred Pearce
Local-first agent analytics with prompt diagnostics
Gal Hadar
Train LLMs to use web search as a tool — trace generation, fine-tuning, and evaluation with Tavily.
Trihedron1240
Tiny LangChain middleware for better tool-call recovery, loop detection, and structured failure messages.
Diagnose context degradation in LLM agents — find where memory breaks and how to fix it
Tristan Neale
Per-tool input validation and output-boundary policies for LangChain agents.
galyarderlabs
An agentic digital characters that live where you already talk: WhatsApp, Telegram, Discord, Slack, Email, and CLI. Give them memory, a face, tools, Google Workspace access, workflow automation, and the ability to send selfies or mirror.
...moreAurite-ai
Agent Verifier is a coding agent skill that verifies code against organizational policies, code quality patterns, security requirements, and framework best practices — before code ships. Works with Claude Code, Cursor, Windsurf, and 30+ agents.
...moredecoy-run
Security scanner for MCP server configurations. Like npm audit, but for your AI agent tool servers. Finds risky tools, input validation gaps, transport vulnerabilities, and over-permissioned capability chains. Open source, zero dependencies.
...moresolar2ain
Proactive perception AI agent framework — continuous mic/camera sensing, smart trigger, streaming voice response. Local-first on Apple Silicon.
...moreInsajin
Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.
...morethinkwee
One-Stop Personal Health AI Agent "Say Hi to Healthy Me"
1337hero
Local LLM BenchMarking
nkhdiscovery
Run a coding agent (Claude/Gemini/Codex) 24/7 on your project. Container-isolated, self-merging, GitHub-driven workflow. Bootstrap any project from your phone.
...moreskillcoffee
The Only Skill That Your AI Agent Needs.
francisco_angulo_de_lafuente
BenchClaw CLI — benchmark any AI agent on the P2PCLAW network (10 dimensions + Tribunal IQ).
tengee
Node installer for Loom plugin and single-skill installation surfaces.
avinashbest
Universal statusline for CLI agents — Claude Code, Cursor, Copilot, and Gemini. Tracks context window, model, usage, and session limits at a glance.
...morenarayan-prem
Read-only AWS connector: Lambda, RDS, S3, DynamoDB, CloudWatch. Built on @narai/connector-toolkit with an approval gate and hardship logging. JSON-envelope CLI + library API.
...morenarayan-prem
Safe, read-only database query connector with guard-rail policy enforcement. Built on @narai/connector-toolkit. Ships a JSON-envelope CLI and a library API. Supports PostgreSQL, MySQL, SQLite, SQL Server, MongoDB, DynamoDB, and Oracle via pluggable driver
...moreZero-friction shared memory for multi-agent AI systems. Pass URL pointers instead of token-expensive blobs.
AgentID integration for LangChain — identity, discovery, and trust for AI agents
AgentID integration for CrewAI — identity and trust for crew agents
Synthetic user research and LLM eval harness — research-grade rigor for developers who can't afford a research team.