Havuz

A blank, working source of truth for Claude Code and Codex across macOS and Linux.

GBase — Recursive Self-Improvement Agent Framework. Memory, evolution, quality gates, identity system, and 40+ auto-registered tools.

Método jurídico aberto e executável por agentes de IA: base curada de STF/STJ, legislação, súmulas, temas e teses; 10 protocolos e motores l

Independent security verification for code written by humans and AI agents. Scan, repair, then prove it — Dvalin runs your project's own che

MCPify is an AI enablement compiler that transforms existing applications into AI-native, agent-operable systems.

Curated skills, plugins, integrations, scripts, and utilities for Hermes Agent.

A hypervisor and sandbox cloud for self-hosting AI agents and RL

Small response modes for AI agents when your head is in a different state.

A kart racing game in the browser with zero art assets — every texture, mesh, material and sound is generated in code. Built by a fleet of C

Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results

Practical, portable skills for agentic coding workflows — clearer diagrams, checked claims, safer GitHub releases, natural EN↔KO writing.

Resource-aware multi-agent orchestration for Codex and DeepSeek Harness (All in Flash DSH plugin)

Local-first, governed documentation for humans and AI agents—mirror Office, PDF, and GitHub sources into linked Markdown knowledge workspace

Find which script, notebook, data, command, or AI agent produced a file — locally, with evidence and honest uncertainty.

An end-to-end encrypted channel between coding agents, anywhere

Markdown-defined provider-backed agents and deterministic workflows for ACP runtimes.

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

Learn what AI skills are and how to design, structure, and use them in real-world agent systems.

AI image and video generation skill for Claude Code and other coding agents — Gemini, OpenAI and Kie AI behind one CLI and MCP server, with

Open Dynamic Workflows: TypeScript CLI runtime for Claude Code-style dynamic workflows across Codex, Claude Code, Gemini, Qwen, Kimi, and cu

give non-vision models the ability to see images by routing images to a vision capable model

Build, inspect, test, and debug Godot games from your terminal. Automate repetitive work with scripts, or let an agent use the same commands

An extremely fast GitHub for pull request review: PRs open in 20 ms. Keyboard-first, macOS and Linux, CLI for coding agents.

Open-source Agentic workflows built using Rust

Let Claude edit your Figma file for you — bulk-rename layers, swap variants, bind colour variables, pour in real copy. Describe the change i

the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours

Run Claude Fable 5 + OpenAI Codex as co-founders in one Claude Code skill. Fable is the Visionary (plan, standards, review), Codex is the In

Local AI multi-agent orchestration desktop app (Tauri · LangGraph)

The security-first skill manager for AI agents — every install runs a security scan. Manage skills & MCP servers across 90 agents. Zero-depe

Open-source knowledge base for people and AI agents. Rich-text editing, hybrid search, GraphRAG, and MCP. Self-host with Docker or use DocsM

Open-source, self-hosted LangGraph Agent Server. Production Postgres + Redis. Same SDK. Same Studio. Zero code changes.

One AI agent, everywhere you work — terminal, desktop, mobile, and your chat apps. Rust core.

铃音的记忆写入协议 - an informatics protocol: fragmented, cue-based, symbolic, highly compressed information for AI agents; usable for memory writing

OpenCode plugin: image generation via your ChatGPT subscription

Let your AI agent use your passwords and API keys - without ever letting it see them

Run your AI agents on machines you already own, as one private P2P mesh. OpenAI-compatible, sandboxed with Podman, signed reputation, no clo

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every g

Open-source sandboxes for AI agents — run untrusted, AI-generated code safely on your own machine.

Your local-first command center for working with AI agents like a real team.

Stop re-explaining yourself

One window for a whole swarm of AI coding agents — split terminals, per-agent git worktrees, live web previews, and a War Room where agents

Secure, reproducible sandboxes for AI agent evaluation, training, and data synthesis.

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

A scrolling terminal multiplexer that tracks your AI coding agents.

Sandbox for running AI coding agents autonomously: isolated, network-restricted, host-safe

I got tired of copy pasting between Claude and Codex, so I made them talk to each other. No API keys, just the subscriptions you already pay

RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB,

Verified AI dependency migrations. Finds which of your lines a version bump actually breaks, fixes them, and proves the result still compile

The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. I

The complete AI video-editing skill: from raw footage and creative direction to one verified final film.