#local-first

A living local memory layer for your coding agents and AI tools.

A collection of tiny, reusable, UI components — wrapped in a helpful app layout with header, side bar, dark mode, and more.

On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.

A local-first, self-evolving terminal AI coding agent based on Pi — reads, edits, and runs code through conversation, and improves its own prompts and skills over time.

Local-first MCP server to query and maintain a Markdown vault from Claude, Cursor, Gemini, Codex & other AI clients - no cloud, no context dump. Guided setup + standalone binaries.

Local-first macOS transcription runtime with Swift services, a Bun CLI, and a TypeScript SDK.

Memoria persistente para agentes de IA. Servidor MCP en Go, local-first y model-free.

Local-first BYOK AI workspace for reusable assistants, prompts, tools, skills, model choices, and private local history across multiple LLM providers.

Agent memory + every context-engineering primitive (write / select / compress / isolate) in one importable library. Ranked recall with activation decay over SQLite/FTS5. One production dependency (better-sqlite3).

Local-first shared memory for AI agents — zero-dependency, governed writes, citations, MCP. Source behind the ihow-memory npm package.

Persistent cross-tool memory for AI coding agents. Single binary. Zero dependencies.

Local Tokenizer/Counter

Codex-native codebase intelligence: deterministic repo context, change-plan drift review, and verification gating for AI coding agents. Local-first, zero API keys.

AI Business Operating System — run your business with AI agents. Local-first, multi-provider, governed.

WeChat/微信 local chat history MCP server for macOS agents. Read messages, contacts, media, favorites, transfers, red packets, Moments and full-text search from local WeChat 4.x data.

realtime speech ⇄ text, 音を字に — wire mic → STT → translate → speech as an on-device voice graph that spans your devices over WebRTC. Runs in the browser (transformers.js/ONNX/WebGPU); no API keys, nothing leaves the device by default.

AI model health monitor for LLM apps – runtime checks for drift, hallucination risk, latency, and JSON/format quality on any OpenAI, Anthropic, or local client.

The full-stack open-source agentic ecosystem.

Local-first shared memory and task coordination for AI coding agents. One Go binary, MCP server, markdown files you own. Hooks for Claude Code and Codex CLI (and their desktop apps).

Private search and Q&A for your documents. One binary that watches your folders and answers questions with citations, fully local.

Free tools that run in your browser — compress images, clean CSVs, rename files, build custom recipes. Powered by Rust & WebAssembly. Files never leave your machine.

🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.

Local-first browser and iOS client for inspecting familiar memory through Coven's validated read APIs.

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.

Run a team of AI coding agents. On your machine. Local-first orchestration for Claude Code, Codex, OpenCode, Antigravity, and Copilot.

An open-source personal agent OS - any LLM, private memory you can see and walk.

Vibe Codr — a local-first coding agent for desktop and terminal, with planning, subagent orchestration, memory, Git review, and any-model support.

Local-first checkpoints and crystals for long-running AI coding agent sessions.

Orchestrate a fleet of real Claude Code agents on your Claude subscription, not per-token API bills - local-first.

Local-first terminal agent runtime with isolated subtasks and intent-aware safety.