Havuz

Voice-first desktop assistant for Windows — talk to your PC and it works inside real apps, safely. By VORNEX.

Turn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts)

Local, live code review for the AI age - read what the agent wrote and send feedback straight back

Run agents like a company. AgentOS is the native control plane for OpenClaw — manage agents, tasks, models, context, approvals, and runtime

My Custom collection of Agent Skills designed for Google Antigravity. It transforms AI coding agents into disciplined, senior-level software

A coordination protocol for small agent swarms, and the pi extension that runs it.

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

Agent Harness Platform — shareable workspaces, MCP tools, skills, memory, and cron/webhook automations. Self-hosted and transparent.

Voice-first Mac assistant that uses the computer for you. GPT-Live-1 voice behind a wake word; brains: Codex, Claude Code, an API or a local

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

One-shot LLM eval cases by NAGI STUDIO - same prompt, different agents (model + harness), runnable artifacts side by side.

Agent Reliability Analyzer: deterministic scanner that finds and fixes AI agent reliability failures

248 small Jev decisions for JavaScript and TypeScript: route, rerank, gate, grade, compare, and label text for agents, RAG, support, code re

Hivekeep is a self-hosted platform of autonomous, persistent personal AI agents. Your AI team. At home.

Production-grade Agent Skills from Evil Martians — drop-in expertise for your AI coding agent

Run agents on a cloud machine. Steer them from your desktop or phone.

An evidence-grounded LLM agent for diagnosing PyTorch training failures and verifying proposed repairs through bounded retraining.

Control 1 or more machines using computer use tools that integrates with your agents

Build your own personal AI agent, one mission at a time. Mission 01: your AI learns who it's working for.

A local-first AI control plane for orchestrating agents, models, tools, and machines from one desktop app.

The agent that evolves with you 𖤍

STEER — AI4R (AI for Research) experiment framework for auto-research and autonomous research. Connect existing research projects and let an

Terminal UI for planning, running and understanding complex agent workflows inside Claude Code.

基于 Go 与 Eino 的多模态视频解读 Agent：阅读转写文本/字幕、按需查看真实画面，将 YouTube 视频整理为图文文章，支持围绕原视频持续问答。

Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents

Native iPhone companion for self-hosted Hermes, with a private authenticated mobile bridge.

pstack. Poteto mode on Hermes Agent

Open Source Alternative to Grok Bot, muse by meta and dots by openai

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

A two-layer coding agent. Your code and data never leave your machine.

AI compiles hallucinated code that pass. This fixes it before accepting it. 100% Deterministic

The factory for custom internal software, purpose-built for human2agent work.

A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional

Zero-Mem: Zero-Token Memory Operations for the pi coding agent (faithful reimplementation of arXiv:2607.29377)

Mercury CLI: multiple AI coding sessions in one terminal. Mix and match provider and locally hosted models, spawn cross-company agents & wor

Machining process planning for motor shafts - input shaft geometry, RAG-grounded operations, machine tools, cutting tools, heat treatment, e

Unofficial typed .NET SDK for the opencode HTTP API

Skillscript — a small declarative language for authoring agent workflows. Runtime, compiler, and CLI.

MCP server for the tastytrade open API: quotes, positions, balances, and dry-run-gated order flow for LLM agents.

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

Draws the work in your beads trackers as trees, with what each agent is doing beside the bead it works. It also watches beads for whatever w

Podplane is a Kubernetes distribution & PaaS you can deploy in a few minutes to your AWS, Google Cloud, or Proxmox VE environment

Observability for AI agents. See what your agent did, why it cost that much, and what to fix.

AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence

ZEOS: a transformer operating system — priority-preemptive scheduling, protected mode, and deterministic replay for LLM jobs

A framework for building intelligent agents

AI agentic skills framework for spec-driven development, built on the organizational model of mafia.

An agent process for building software meant to last

Benchmarking headless browsers as agent runtimes

让你的 AI 智能体们组成一个团队：在任意宿主里把任务派给本地订阅的 Claude Code / Codex / Grok / Kimi / Antigravity，并行、不打断对话、全走已有订阅。