Havuz

Production-Grade AI Agent Development Full-Chain Guide: Development, Testing, and Base Framework

Open-source canvas for orchestrating Claude Code, Codex, and other CLI agents. Run agents in parallel, delegate tasks, and let AI build reus

Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforce

Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-mo

Portable multi-agent AI developer setup for Claude Code + Ollama. Role-based local LLM orchestration via Bash — plan, code, review, commit.

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

Local-first AI companion daemon — an agent harness with its own long-term memory. Remembers you, grows with you, extends and repairs itself.

GNAP — Git-Native Agent Protocol. RFC Draft for git-based agent orchestration. Zero servers.

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

Run coding agents unattended. Agents write the code. Axocoatl writes the receipt. Claude Code, Codex or a local model in a sandbox; the host

Shared memory for your AI agents: a fact one agent writes on one machine is there for the next agent and the next machine, with no server in

Self-tuning multi-agent AI trading system. 8-source signal fusion, Bull/Bear/Judge debate on Claude Opus 4.7, Kelly + ATR position sizing. P

AgentScope Golang: Agent-Oriented Programming for Building LLM Applications

Dispatch your task backlog to local, interactive AI coding agents. One git worktree per task, sandboxed by default.

Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.

The visual Kanban for long-running AI agents. Watch your agent's plan organize itself: dependencies unlock into Ready, the critical path lig

Agentic IDE with custom harness

Strands-based agents and harnesses for agentic benchmarks.

Turn Hermes into an autonomous WhatsApp manager. Take full control of your messaging. Forget typing: schedule messages, send voice notes, sh

开源桌面 AI Agent 与 CLI：长期记忆、多 Agent、实时语音；Qwen3.8-27B Coder390 EfficientThink 本地 GGUF（llama.cpp Q2/Q3，内置 Q4 MTP）· Open-source desktop AI agent &

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

Open WebUI tool port of Superpowers by Jesse Vincent — brainstorm → spec → plan → execute agentic dev workflow for local LLMs

One command to install, heal & prove ruflo (claude-flow) + agentic-qe + RuvNet Brain — plus ambidextrous Claude/Codex/OpenCode host routing,

Idea-to-store autonomous harness for Flutter/Flame games across Claude Code, Antigravity, and Codex. Automates research, planning, design, g

Optimize LLM agent harnesses through tunable Formulas to dynamically enhance the agent, and improve those Formulas with optimizers based on

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

Открытый бенчмарк LLM: какая нейросеть лучше пишет код 1С:Предприятие (BSL). Объективная оценка LLM по методике SMOP с реальным исполнением

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

TUI Music Player - now agent native!

ZhuLing — Zero-config AI Agent framework for Java. One YAML to launch Agents on Spring AI + DDD, with MCP tools, full observability and a Re

Personal AI agent harness powered by Claude Code. Always-on access through Discord, Telegram, or a built-in web UI.

Open-source Claude Code plugin porting the internal /skillify skill: turn a finished session's repeatable workflow into a reusable SKILL.md

Translate books and documents with LLMs, featuring glossary extraction, review, and polishing pipelines.

CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?

One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, and 75% token savings

Where agents build agents. An open-source Rust framework for complex agentic systems: ontology-grounded, auditable, one binary.

Self-hosted AI agent that builds apps. Chat with a coding agent (Claude Code or Codex) that builds mini-apps, modifies its own UI, and gets

Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings

A cross-platform agent framework and samples, support on Windows/MacOS/Android/iOS/HarmonyOS

The open-source cloud for the agentic era. Don't pick a database, a region, or a RAM slider - your coding agent and Bay decide, then keep th

An AI agent for your desktop and terminal.

一个用 C# .NET 10 写的 Agentic 框架，采用 ReAct 范式，支持渐进式技能 (Skill) 加载、 多个大模型 Provider、MCP Server、图像识别、流式 WebAPI、React WebUI、钉钉集成。

Household Warehouse Management System powered by Maid-AL1S

An agnostic AI-driven exploratory test framework that intelligently explores, tests, and validates any application

Cyber Threat Intelligence Skills for each stage of the CTI Lifecycle.

Safe to explore. Free to build. Koder by aixplain is an AI coding harness for desktop and terminal, with permission checks, reviewable chang

为 Token 燃烧而生：token 越来越便宜，质量永远稀缺——与其省 token，不如把它当燃料烧。同一道题派最多 1000 个 agent 并行竞赛、裁判择优，用冗余换质量。Go 写的开源终端 Coding Agent，类 Claude Code，可接入任意模型，对团队友好

Agent-powered iterative optimization: put an AI agent in a verified improvement loop.

Symbio is a self fine tuning AI agent that gives power to users through seamless interaction with their machines. This flexible system adapt

Nausicaa treats an Agent run as a dynamic topology of Lanes rather than one fixed linear loop. The model can decide when to observe, fan out