Autonomous AI agents that perform tasks independently
Auditable BDI (belief-desire-intention) agents with LLM deliberation — explicit beliefs, committed intentions, and a trace that answers 'why'
...moreedisonssszzz
A portable, headless LLM Wiki — compile knowledge once, maintain it continuously. CLI.
mohamedzhioua
Proof-of-done gate that makes AI agents prove a task is done before claiming it.
elkindev
Database schema graph for AI agents — index your database catalog into a local graph, served over MCP
elkindev
Database schema graph for AI agents — index your database catalog into a local graph, served over MCP
elassoulidev
Measure whether the code an AI agent built matches the spec it was given.
_retro_
Query SQL databases in natural language using an AI agent. PostgreSQL, MySQL and SQLite.
downingmoon
AgentFeed CLI for sharing privacy-safe AI agent worklogs — never your code.
GitHub Actions
Host-agnostic bioinformatics agent harness — hand-rolled agent loop, DBOS-durable workflows, sandboxed compute.
clubanderson
Pluk structured events from AI agent terminal output — classify, subscribe, and react to JSONL event streams
AgentGuard
AgentGuard CLI — the deployment gate that blocks unsafe AI agents in CI.
yui-stingray
Pure-function policy matrix evaluator for AI coding agents (repo x capability x context -> deny/require_approval/auto_allow).
...morelarslll
EggAgent — self-improving AI agent framework (all-in-one)
johnny0120
OpenCode plugin that predicts your next message and shows it as ghost text — role-plays as you using your conversation history. /pred-on to enable.
...moreChinmay Kakatkar
Property testing framework for agentic AI
Yamen AlBarghouthi
An air-traffic-control protocol for coordinating irreversible actions across multi-agent LLM systems, with a LangGraph adapter.
...moreRudrendu Paul, Sourav Nandy
Compare AI coding tool spend before and after a migration -- Cursor, Claude Code, GitHub Copilot, OpenCode, and Codex CLI, real numbers pulled from each vendor's own API or local logs, one command, zero runtime dependencies.
...moreRudrendu Paul, Sourav Nandy
Regression-testing CI gate for self-edited Claude Agent Skills (SKILL.md, MEMORY.md): golden-transcript record/replay against a skill's own declared and inferred capability surface, zero hosted infrastructure.
...moreRudrendu Paul, Sourav Nandy
AI agent observability with deterministic record/replay — capture any LangGraph or OpenAI Agents SDK run, replay it offline at zero API cost.
...moreSERPdive
Official Python SDK for SERPdive, the AI Search API: answer-ready web content for LLMs and agents
Python SDK for DAF (Declarative Agentic Framework)
A local-first API gateway for open-source LLMs: auth, RAG memory extension, DB connectors, token accounting, and a built-in coding agent.
...moreRicky-7-Yan
Enterprise audit agent workspace with Agentic RAG, governed tool use, evaluation harness, memory, and human-review delivery workflows.
...moretwz007
Framework-agnostic Java observability sidecar agent: chat with a live JVM via MCP/web UI (metrics, slow calls, errors, logs, thread dumps, method traces). Self-hosted, attachable (Arthas-style). Apache-2.0.
...more