Havuz

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and

Deterministic agent reliability detection rules for the Trustabl Analyzer

The implementation for SIGIR 2026: Learning to Retrieve from Agent Trajectories.

A macOS desktop AI pet that mirrors your Claude Code & Codex CLI session state in real time. 支持Claude Code和Codex CLI 的像素风AI桌面宠物，会话状态实时映射，支持导

A beautiful home for your Hermes agents. Chat with them one at a time or all together, connect your apps, and reach them from the browser, y

Hive Agents harnest agent loop localfirts

"Multi-Agent Team — 让31位导演大师成为你的AI创作团队"

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

纯 Dart 实现的 AI Agent 管理框架

Use Claude Code models on any OpenAI-compatible client with no API charge.

Lightweight agent multiplexer, all in one Web dashboard

基于 2.1.88 版本自维护的开源 Claude Code Cli，甚至支持 OpenAI 订阅和使用 Codex Apps

Your AI agent can now search Youtube, watch videos, create highlight reels, and more

Lightweight Linux sandbox for AI agents. Kernel-native isolation (namespaces, cgroups, seccomp, Landlock) with REST API, MCP bridge, and web

An open-source Python SDK for analyzing, evaluating, and curating agent traces stored in BigQuery. Built on top of the BigQuery Agent Analyt

一款跨平台智能笔记 Agent 应用，支持多格式笔记、本地知识库、AI 智能助手、向量语义检索 。

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.

A terminal AI agent you can fully undo - every file and shell action is snapshotted and reversible. Model-agnostic (any LLM), and connects t

可视化 Agent 编排平台｜基于 DeepSeek Harness，支持 Workflow、Multi-Agent、元编排、MCP 与 Human-in-the-loop｜Visual AI Agent orchestration platform for workflows,

🏆 AI Agent 生态排行榜：Skills · MCP 服务器 · Prompt 库 · 框架 · 深度研究，按 GitHub Stars 每日更新 | Leaderboard for AI agent ecosystem — Skills, MCP, Prompts,

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

Evaluating frontier models on real-world ai-infra engineering tasks

Local-first cross-session long-term memory for DeepSeek Harness — 22 narrow tools, hybrid FTS5 + local-vector retrieval, evidence gate, prov

An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harnes

Angles Code CLI — 2MB coding agent with 2GB powers

Git-Native Coding Agent for Mac

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

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

controls the entropy of the codebase by enforcing code module boundaries.

AdalFlow Alternative 2026: Auto-Optimize LLM Apps Without Code

[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

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

Build & Auto-Optimize LLM Apps in 2026: The Ultimate AdalFlow Guide

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

🤖 LLM Engineering Roadmap — Complete Developer Guide

Tidy is an open-source agentic development environment for engineers and designers. Apache-2.0.

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

Official benchmark reproduction code for the SAG paper

The bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability

Neuroscience-inspired memory framework for AI agents

Rhizome lets Claude Code, Codex, and OpenCode sessions discover each other, follow selected work, and exchange messages through MCP. Use it

The Ultimate AI Compute Gateway ( Router ) | A high-performance, stateless-to-stateful LLM compute gateway in Go. Features multi-model pooli

跨 agent 的 skill 管理器 + skill 推广工具，欢迎fork和pr。管理你所有 skill ，创建技能自带讲解pdf或ppt。支持各种Agent。

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

Tells your AI agent which parts of your idea already exist on GitHub, which to adapt, and which to just write — every repo verified live. MC

Desktop app built on Claude Code harness for proactive engineers.

A AI Agent development platform.

Benchmarking Agents on Real-World Terminal Tasks

A terminal-native AI agent runtime built in Rust. Interactive chat, parallel agent orchestration, and autonomous supervision.