Autonomous AI agents that perform tasks independently
Wei-Chih Chen <[email protected]>
A quality gate and spend auditor for your AI agent fleet.
Rawson Consulting B.V.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
AgentCulture
A cooperative/competitive strategy arena where agent teams complete missions, control objectives, manage resources, and out-coordinate opposing teams.
...morePython SDK for Agent Communication Hub — multi-agent messaging, task scheduling, shared memory
Vineetha Vallish Kumar
Evaluation framework for multi-agent AI workflows: handoff quality scoring, failure attribution, loop detection, and cost guardrails.
...moreWilliam Liu
Local AI search engine for your files and agents — hybrid BM25 + vector semantic search in one SQLite file. CPU-only, offline, no LLM in the query path.
...moreupbit-official
Build and backtest Upbit trading strategies by chatting with an AI agent (Claude Code, Codex, Cursor). Backtest-only, beta.
...moreamajorai
Ryu — open-core orchestration engine + LLM gateway for AI agents. Local-first, BYO everything.
Haochenhust
A self-evolving personal AI agent on Feishu/Lark: nightly reflection, autonomous learning, and knowledge graduation on top of a coding-agent harness (Claude Code / Codex)
...morenikoniko777satoshi-alt
An operating system for coding agents — reproduce a top-tier model's behavior with structure, not spend. by Sumika
GitHub Actions
CLI and AI-agent skill for self-hosted Huly — manage issues, projects, channels, documents, calendar, time tracking, and more from the terminal or CI/CD
...moreGitHub Actions
Vault-native agents for Claude Code — a #agent/definition note + an inbound message becomes a sandboxed claude turn; the reply is written back as a note. Messaging gateway on :1941.
...moremaulanashalihin
Pi extension — describe images via vision model when your active model cannot see images directly
ddfourtwo
Drafted — visual thinking surface for humans and AI agents. Renders HTML, markdown, images, and code as frames on a zoomable canvas, with MCP tools for AI agents and real-time sync for humans.
...moreGitHub Actions
SiliconFlow AI model plugin for XpertAI platform
zalom
Intent-driven idea development system for AI coding agents
readfor
AI coding agent powered by Doubao (豆包) via browser automation (doubao.com/chat/) — no API key needed. Performance-optimized. Enhanced with comprehensive security.
...moreCrucible. The touchstone — benchmark and verification tool for multi-agent dispatch.
shiersa
Local-first software factory: deterministic multi-agent orchestration for small local models. Early development.
AgentCulture
Agent + CLI that turns Claude into a private Spanish tutor: track progress, get an overview, get advice, read stories, and learn & practice Spanish (written and spoken) online from your phone.
...moreAgentCulture
Agent + CLI that turns Claude into a private French tutor: track progress, get an overview, get advice, read stories, and learn & practice French (written and spoken) online from your phone.
...moreRyan Lindgren
Testing-shaped eval framework for Agentick. defineEval(...) returns a callable with runtime parameterization; .matrix(axes) runs cartesian parameter sweeps — e.g. the same document/expected pairs across multiple models — and reports per-cell results.
...moreZijian Zhao, Yulong Hu, Sen Li
A multi-agent ride-pooling & dispatching simulation environment for transportation gig-market research.
Deterministic, local-first observability for RAG and agentic pipelines (umbrella package + analyst CLI)