Havuz

Documentation and examples around deploying LangChain agents

Run any AI agent — Claude Code, GAP, LangGraph DeepAgents — in a hermetic sandbox. Reference implementation of the Harness Protocol.

基于 B 站博主 黑鸦（Heya）视频标题的深度分析，让 AI 学会黑鸦的标志性风格：长标题、情绪炸弹、多事件合并。

Observable, portable, composable TypeScript agents and runtime.

A minimal, explicit, provider-safe harness for the Pi coding agent

The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents o

Give your agents a simple way to host static sites.

OpenMayhem is an open-source and decentralized inference router for consumer & pro hardware. Providers earn, users/agents access cheap infer

Visual plan mode for AI Agents instead of giant walls of text 📝

Skills for agents

Deepy - Vibe coding for DeepSeek models in your terminal

Multi-agent shared brain across Claude Code/Desktop, Codex, Gemini, Copilot, VS Code. Cross-session memory, self-improving skill loops, inte

A JAX transport-economy learning environment for route planning, cargo flow, financing, and replayable agent benchmarks.

Snap a line before your agents build.

Shared Python libraries that Foundry-built agents install and extend — core protocols & DI, config loading, FastAPI HTTP layer, and AWS Stra

Package manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code,

Orchestration of autonomous, collaborative AI agents in Go — an idiomatic Go port of CrewAI.

AiGuard —— 本地优先的 AI 流量安全网关：本机 MITM 代理只接管 AI 域名，请求侧脱敏、响应侧流式还原，并识别七类风险信号。原文不落盘、不上传。（注意如果你需要模型直接使用token或者其他密钥进行操作，请放入白名单或关闭该功能！！！！）

Guardrails for the agent harness. Regulated data stays on your machine, and every prompt and tool call is scanned before it runs.

Fold finished episodes out of pi's context, and recall, ask or fork them instead of compacting

Local-first control plane for long-running and multi-agent AI systems. Observe, steer, recover and orchestrate agents.

Research into flattening compaction strategics

Stellar MCP server for AI agents: one authenticated gateway to official docs, live ecosystem data, community intel, and tested playbooks.

Publish HTML for agents — one API call, MCP server included

WikiSkill, agent oturumlarından kalıcı wiki bilgisi derleyip skill değişikliklerini doğrulama testleriyle kabul veya geri alan bir Python aracıdır.

Neden yükseliyor · Agent'lar için kalıcı bilgi ve self-improvement ilgisinin yüksek olduğu bir dönemde, araştırma makalesindeki döngüyü gerçek agent çalıştırmalarıyla uygulanabilir bir araca dönüştürdüğünü öne sürüyor. 29 günlük yaşına göre 250 yıldız ve son 28 günde 22 commit dikkat çekici; ancak yalnızca 2 farklı yazar var ve yıldızlar kullanım ya da etkinin kanıtı değil.

Write once. Store anywhere.

A Dynamic Island-style command center for managing all your AI coding agents on macOS.

More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

Kanwas — Shared context board for teams and agents

Event-sourced graph runtime for durable and stateful agents

Multi-agent AI pipeline that turns one line of text into a finished short-form drama: script, cinematic storyboards, character-consistent vi

CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.

Agentspan is now part of Orkes Conductor

shadcn/ui, but for building agents. 🤖

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

Your First LLM-Wiki Conversation Knowledge Base

The missing bridge between your ML models and your AI agents.

Ridiculous speed. Readable code.

Open-source app builder engine — intent to working app

The open-source thread-plane for agents: chat, durable threads, persistence, human approvals, and generative UI for Angular, on LangGraph an

AI驱动的一站式论文搜集、写作、精读论文、协同助写方案

Automated friction logging for agents.

Tactical AI Workspace Monitor & EDR

Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops to company infrastructure with

Open-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in

Skills Constitution — meta-rule governing all skill invocations across agent platforms

Run many Claude Code (or Codex) sessions in parallel — across every project — from one screen. Local-first, git-worktree-isolated tasks, no

A secure, stable, and lightweight alternative to OpenClaw and Hermes.

Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses).

MergeOS — bounty marketplace, ledger, scan, and agent protocol platform