Search

The harness that makes consumer-GPU models feel first-class. Local-first: no telemetry, no account, no cloud tier.

ChaChaChat - A simple, embeddable LLM chat with RAG capabilities

An AI agent framework for building LLM-powered applications

Garden-citizen dispatch for pi, Claude Code, Copilot CLI, OMP, Antigravity, and Codex; visible tmux sibling seats for Pi/Claude/Copilot/OMP/Codex, preserving each harness's auth, tools, and transcript; plus Claude/Cortex ACP.

Local-first multimodal AI agent with private RAG, memory, OCR, web tools and local LLMs.

Local AI coding-agent status, alerts and focus for Stream Deck Mini, MK.2 and XL

Build agent instructions from your project's sources.

Quality-preserving local context optimization runtime for LLM clients

CLI to scaffold and manage AI agent skills across projects — like shadcn/ui, but for Cursor, Claude, Codex, Copilot, Antigravity, and more

Local Hexagon NPU terminal agent for Snapdragon X Elite Windows ARM64

A shared coordination board for AI coding agents driven by different people

One API over the coding agents installed on a machine: Claude Code, Codex, Cursor, and more.

Stamp out a new Claude Code agent from the canopy operating model — a self-contained, zero-runtime-dependency factory. Pip-installable into canopy / canopy-web / any second consumer.

Tools by AIs for AIs

An educational example agent built with LangChain, LangGraph, a local Ollama model, and one MCP tool. It scans news and price data for a narrow scope: equities (stocks) and ETFs only. It is a news/trend summarizer, not a financial advisor -- it never recommends buying or selling anything.

Build your team of AI agents without the pain of prompt chaos, wide-open keys, MCP overload, and a free-for-all on your machine. Declare each persona (bro) once, with its prompt, tools, secrets, procedures, and whom it may summon, and it comes to life in its own sandbox holding exactly that, on any harness, any model

Multi-platform AI bot framework: 5 hot-swappable agent runtimes (Claude Code / OpenClaw / Kilo / Gemini CLI / DeepSeek Harness) across Discord, Feishu, DingTalk and a self-hosted web entrance, with shared memory, bot-to-bot collaboration and real-time voice.

Replay Claude agent sessions with JEP-compatible accountability events, tool lineage, delegation flow, and verification state.

JEP middleware for OpenAI Agents SDK portable accountability semantics.

Universal LLM FinOps cost and token tracking plugin for Google Agent Development Kit (ADK) and Python agent frameworks.