#ai-agents

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

Distribute AI Skills as Composer dependencies

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

CLI to manage persistent thoughts and notes across repositories, with AI coding agent integration.

AI-first CLI for Semaphore CI/CD. 80+ tools, embedded MCP server, JSON output

Open-source workflow engine for AI agents. An agent calls Realm over MCP, or realm agent drives a model from the CLI. Steps run in order, agent answers are checked against the schema a step declares, human gates pause the run until answered, and each finished step is recorded.

AI-powered product lifecycle orchestrator — takes a product idea from intent to shipped code through agent-driven pipelines (Claude + Codex) with human gates, postconditions, and auditable traces.

Zero-dep agent workflows with structured approval gates and adversarial review.

A dev agent multiplexer for git worktrees and coding agents.

A multi-agent context, rules, and hooks boilerplate generator. With a single command, it scaffolds conventions, namespaced skills, stack-appropriate settings, and interactive guardrails for seven major AI coding environments, matching each agent's native file formats and capability profiles.

Quality-gated autonomous mission completion loop for Claude Code and Codex (plan, execute, review, score, iterate).

Ten agent sessions, one screen. A tmux-based TUI for Claude Code, Codex and opencode — see which agent is waiting on you, give each its own git worktree, and resume after a reboot.

Local-first control plane for AI coding agents: repo memory, verification, sessions, and dynamic workflows.

ztrack: evidence-gated task tracking for AI agents

Spec + Test Driven Development — markdown-first methodology kit for AI coding agents. The docs edit is the spec; tests gate behavior; working artifacts are never committed.

Leave notes in the margins of your repo's docs then let your AI agent apply them, resolve the threads, and journal what changed & why.

the trust layer for agent memory

aiwf is a Git-native kernel for human+AI projects: plans, decisions, and provenance, gated and validated at every commit.

X-ray vision and hands for AI agents inside Tauri apps — DOM, IPC, Rust backend, and database through one embedded MCP server. 35 tools. Zero production cost.

Open-source TypeScript framework for persistent human-agent collaboration, with shared artifacts, human approvals and controlled execution on your infrastructure.

AI trading brain for crypto perps — composite signals, funding rate arb scanning, and market regime detection via MCP

Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.

Local, human-in-the-loop message bus for coordinating parallel AI coding-agent sessions on one machine

Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.

mosADD™ — open MCP toolkit as Irondome' omnichannel messenger for the agentic and robotic era. Tools across every module — mDM, mIRC, mURL, mAYL. Add it once per tool; then your agent shows up in the grid and posts [need-human] when it needs you.

공공데이터 덕후, 오데덕. AI 에이전트가 목표에 맞는 자료를 찾고, 자동 활용신청·수집·연결·분석을 거쳐 결과와 근거를 만들도록 돕는 오픈소스 실행 플랫폼.

🩺 Doctor for your repo's AI harness — audit, merge & drift-guard scattered agent configs (AGENTS.md / CLAUDE.md / .cursorrules) into one source of truth. Real evals: 6/28 → 28/28 correct, −27% latency. Field-tested on react, vscode, n8n + 11 more. Claude Code · Codex · Cursor · Gemini

AI-native service workbench: MCP server + shared daemon for Claude Code, Codex, and Gemini. CLI, TUI, and web dashboard for running services, logs, git, and databases.

No repository description published.

Two-layer enforcement (pre-commit hook + CI mirror) for small teams using AI agents. Catches debug leaks, file growth, secrets, and forbidden patterns before they merge, and scaffold-doctor tells you when a guardrail is installed but not actually running.