Autonomous AI agents that perform tasks independently
AgenticFI
Authenticated local OpenAI-compatible proxy for the Onchain Router Buyer Runtime
LLMS-Explorer Contributors
Read-only CLI and TUI over the generated llms-explorer concept tree and llms-concept-abstractor concept packs, plus a thin CLI over the skills SDK
...moreBrianV1981
A modern, terminal-based dashboard for managing tmux workspaces. Built with Python Textual, it features a command palette, live previews, robust session persistence, and seamless zero-friction resumption for AI coding agents.
...moredougransom
Prolog Agent Framework, Reusable Agent Skills, MCP Server Pattern, Neurosymbolic AI, and Safe Multi-Engine Execution (Scryer, SWI, Trealla, Tau).
...moreDetect and recover tool calls trapped inside a model's reasoning channel — the reasoning-channel swallow bug class across vLLM, SGLang, and llama.cpp. 1:1 mirror of the TypeScript library.
...moreAleix Navarro Garrido, Ricard Garcia-Carbonell
Multi-agent LLM peer-review framework (an editorial board for manuscripts)
lacrous
Provider-agnostic LLM client SDK — streaming, tool calling, circuit breaker, retry, reasoning normalization, cost enforcement, and SSRF-safe provider registration for OpenAI, Anthropic, Gemini, Azure, Groq, and Ollama. Zero runtime dependencies.
...morevabelous
Production-oriented Meilisearch workflow and AI Agent nodes for n8n
Binary Bourbon
Run coding agents on Fountain, with real computers, repositories, and credentials.
Security Gate Team <[email protected]>
Ultra-low latency (<10ms) deterministic security, prompt injection, secret leak, dangerous AST, and factual hallucination inspection micro-oracle for autonomous agents on Polygon, Base, and Arbitrum.
...moreMichael Crowe <[email protected]>
Crowe Agent Kernel — the one provider-agnostic agent loop the Crowe ecosystem mounts.
William Caban <[email protected]>
Workspace Knowledge Protocol — progressive disclosure knowledge index for agent frameworks
orangecxcx
Agent-plane presentation selector: composes one agent's tools as PTC mode, native, or both
openvurp
A wallet of AI agents that use real tools and ask each other when a question isn't theirs. Runs on your computer; the model is your choice, local or not.
...moreDJG3DK
Autonomous coding agent built on LangGraph + deepagents. It natively plans, builds, verifies, and ships real production changes with a built-in human-in-the-loop review stage.
...moremediajunkie
Intelligent Product Management Assistant - v1.0
xingchen20lj
Evidence-gated vulnerability research for AI security agents.
GitHub Actions
Verify AI agent transactions with FLINT before money moves or paid service is delivered.
kolatts
The Paperwork Nightmare CLI — structured JSON access to Jira, Bitbucket, GitHub, Confluence, Azure DevOps, SonarQube, Jenkins, and more, built for AI coding agents. One command does what three meetings couldn't.
...moreGitHub Actions
Partner SDK for the Asterisk AI Agent Gateway realtime protocol v1
"DigitalKin.ai" <[email protected]>
Python gRPC interfaces for Agentic Mesh Protocol
Official LangChain & CrewAI Integration for OpticParse Zero-CSS Multimodal Vision Web Scraping & PhishVision Threat Detection
...moreCodex Agentic Utils contributors
Codex-native ADR and architecture-design skills with reusable specialist agents
patibandlavenkatamanideep
Production-shaped control plane for AI support agents: scoped routing, policy broker, tool boundaries, approval queue, replay verification, audit traces, and human handoff. Prototype on synthetic/sample data — no production users.
...more