#local-first

Terminal coding agent for local LLMs (llama.cpp, Ollama, vLLM) and any OpenAI-compatible API. OS-sandboxed autonomy, MCP, sessions. Go.

Run AI agents on machines you control, alone or as a whole organization: Slack, WhatsApp, Pages, Bases and SDKs generated from the CLI

该仓库未发布描述。

Confidential local RAG for your coding agents.

Local UI for Beads — Collaborate on issues with your coding agent.

Local Go daemon that gives AI tools persistent shared workspace state. Context assembly, multi-provider inference routing, hash-chained ledger, MCP server.

Terminal-based, Agent-friendly Ticketing System

Store, share, and resume AI coding sessions.

Experimental local-first memory CLI for MCP agents: read-only Gmail, calendars, iMessage, and files → cited local context

Edit DOCX/XLSX/PPTX in your browser — client-side, no server, works offline (OnlyOffice + WebAssembly)

json-joy is a library that implements cutting-edge real-time and collaborative editing algorithms and utilities for JSON data models, with a focus on developing the JSON CRDT (Conflict-free Replicated Data Type) specification and implementation.

Knowledge Management for Humans and Agents

Evidence-backed proof of done for Claude Code, Codex, Cursor, and other AI coding agents. Run real checks, bind results to current Git state, and know what is ready for human review.

Self-hosted family AI gateway with parental controls. Runs on Linux, macOS, and Android (Termux) — Raspberry Pi, mini PC, old laptop, homelab server, even a phone. Telegram, Discord, web. Privacy-first, works with any LLM (local or cloud), OPA content filtering, MCP skill scanning.

A local workbench for agents doing continuous work across sessions, commands, human input, and external events.

Your work, already underway. A personal AI assistant for your job: mail, chats and tickets become tasks, the agents you already use (Claude Code, Codex, Gemini) do the work, and nothing goes out until you approve. Open source, runs on your machine.

Prosemirror Binding for Loro

Shared, persistent memory for AI assistants, built on the Zettelkasten method

Local credential control for AI coding agents.

Local-first control plane for AI coding agents — launch browser terminals, run and remotely control sessions, and track files, tokens & cost across Claude Code, Codex, Cursor, Gemini CLI and 20+ more. 100% local, no telemetry.

A POSIX shell with AI in the grammar: type ?? to drive Claude Code, Cursor CLI, Gemini CLI, or Ollama over ACP. Local-first, no login, no telemetry.

Open-source, local-first personal AI. Chat with Ada, delegate tasks, and work with files and projects using cloud or local models.

Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.

Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.

Self-hosted mission control for real Claude Code and Codex sessions — persistent terminals, automations, and browser/mobile control.

Local-first MCP server for AI-powered codebase intelligence — AST analysis, dependency graphs, and semantic search. Your source code never leaves your machine.

The AI-native application framework for Python — reactive UIs, APIs, agents, workers, realtime, MCP, and durable execution in one runtime.

The only SEO skill your agent needs. 70+ SEO audit tools through a local CLI and MCP server, using your own crawl, Search Console, and GA4 data.

A local CLI that links findings you write to the command runs that informed them, so you can find them before similar work.

Simple network programming on top of Tailscale.