Havuz

Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。

AI-powered mobile automation agent — describe what you want in plain English, AppClaw reads the screen, reasons, and acts. LLM-agnostic, ope

Hermes Agent plugin for cron analytics and observability. The dashboard for agentic automations in Hermes.

OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command evidence, verification gates, impact a

Open-source control plane for AI agents on your own Kubernetes infrastructure, with per-agent costs, access controls, and audit logs.

Local multi-agent harness for running persistent agent teams, long-run, society-simulation

600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.

WebView automation for Kotlin Multiplatform. Run page workflows in an embedded WebView on Android, iOS and desktop, from your app, a test, o

AI Agent 面试知识库：覆盖 LLM、Prompt、RAG、MCP、Tool Use、Agent 架构、Multi-Agent、LangGraph、Claude Code、Codex CLI、工程化评估、安全与源码解析。

BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit sever

Pan by Euraika — a self-hosted AI workspace for Hermes Agent. Chat, skills, extensions, memory, profiles, and runtime controls.

A configurable Bash/PowerShell loop that runs an AI coding CLI with a fresh session each iteration

Multi-Agent Mesh · Connect · Orchestrate · Scale

TypeScript interpreter for AI agents. Written in Rust. 2µs cold start. Sandboxed. Alternative to MCP tool calling.

Multi-Agent AI 工作台 (AgentCore) — 真正的 Agent 团队协作，而非单 Agent 子任务派发

Graphon is a Python graph execution engine for agentic AI workflows.

Continual harness optimization

Unified Harness TUI (ACP client). Self-Improvement TUI plugin of DeepSeek Harness. Everything Here Is Also A Plugin.

Open-source AI agent runtime built in Rust. Define once, deploy isolated instances per tenant with built-in memory, encrypted vault, self-ex

Build a coding agent from scratch, one harness primitive at a time. 15 chapters (ch-00..ch-14), each green on two gates.

If you can read ~200 lines of Python, you understand MCP.

🦀 Open-source alternative to Claude Code, built from scratch in Rust. Agentic coding CLI — thinks, plans, and executes with any LLM. Compati

A modern Go framework for building multi-agent AI systems.

Isometric architecture diagrams as code — text DSL in, design-grade 2.5D SVG out. Agent-first: LLMs can discover, generate, and validate the

Self-host your own AI app builder: FOSS v0/Lovable like.

A nightly newspaper that writes itself: an agent runs the desks, the figures come from code, and it refuses to publish an edition with marks

Write JSONL/XML. Render video/image. Built for agents.

One-Stop Personal Health AI Agent "Say Hi to Healthy Me"

The agent for perfectionists – Crafted in every detail

Daily AI brief for indie builders — what to ship, what to skip, who's eating whose lunch. Bilingual.

Generative UI SDK for Swift (genui)

Read what your agent wrote before you say LGTM. A fast TUI in Zig for reviewing code with vim motions.

⛵ Native tools that agents can rely on.

Device Context Protocol — bridge LLM agents to physical devices. Sub-50-byte frames, 27.6KB flash / 0.6KB RAM measured on ESP32, capability-

A local review board for work an agent wants a human to look at — agent publishes, you annotate in the browser, feedback flows back as JSON.

【ICML2026 Spotlight】 T2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning

Durable iMessage AI agent template. Text your agent, get retryable LLM + tool replies, full observability. Production-ready, deployed on Ver

zuoge — open-source AI design workspace with a document-derived SoA infinite artboard and Design Agent

Neuroscience-inspired memory framework for AI agents

[ACL 2026] PIArena: A Platform for Prompt Injection Evaluation

多智能体小说写作框架 | Multi-agent novel-writing framework — 每个角色都有自己的脑子,每一章都有质量门禁

Generalizing ARIS from 科研 to 研究 — same five-step loop (plan · draft · adversarial review · iterate · persist) applied beyond academic resear

Verifiable AI coding agent harness / 可验证的 AI 编码代理：evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP

HippoBuddy — AI-powered desktop assistant for chat, coding, and office workflows.

A free, open-source coding agent inside VS Code.

导师skill，让导师再次伟大！Make Supervisor Great Again！Inspired by colleague-skill（同事skill）and ex-skill (前任skill)

OpenCode plugin for automatic API-key failover and rotation across multiple provider keys

Map an online Overleaf project to a local Git-backed working repository.

Android AI agent app. Kotlin + Rust via UniFFI.

Sandboxed OCI container images for AI coding agents, built reproducibly with Nix.