local-first

Belay is an open-source, local-first security layer for AI coding agents. It blocks dangerous commands, secret leaks, prompt injection, and risky MCP tool calls, with human approval flows and support for multiple agents.

A local-first annotation UI for reviewing and revising agent plans before approval. It opens a browser-based interface, lets you mark up plans with structured feedback, and sends changes back to supported agents like Claude Code, OpenCode, and Pi.

CodeTrain is a hands-on AI coding trainer that teaches developers on their own codebase by making them write each step themselves, with hints, test runs, and progress tracking.

NeatContext is a local-first desktop workspace that adds team-specific knowledge and read-only internal tools to LLMs so they can give grounded operational answers. The page shows incident-response examples, Markdown-based profiles, MCP integration, and support for multiple model providers.

LocalMask is a local-first privacy layer for AI coding that scans repos on-device, masks secrets and PII into reversible tokens, and forwards only safe content to models like Claude, GPT, or Gemini. It also supports masked repo mirrors, an AI proxy, and a CLI/MCP workflow.

Local browser-control tool that lets coding agents drive a signed-in Chromium browser through a CLI, daemon, and extension.

Rowboat is an open-source desktop AI coworker that keeps long-term memory in a local Markdown knowledge graph and includes built-in surfaces like email, browser, notes, meeting transcription, and code mode.

Excalibur is an open-source AI coding agent for product engineers. It runs from the terminal, supports multiple model providers, and covers the full workflow from discovery and planning through implementation, verification, review, and shipping.

Slashspace is a local-first infinite canvas for AI chat and agentic work, designed for research, writing, development, and long-form thinking. It supports multiple models, MCP connections, local storage, and desktop apps for Mac, Windows, and Linux.

Local-first desktop app for AI document translation and side-by-side comparison, with support for multiple engines and cloud APIs.

Local-first AI memory layer for LLM apps with persistent knowledge graph storage, entity extraction, semantic retrieval, and API endpoints for ingesting and retrieving context.

Local-first Node tool that reads Claude Code and Codex logs to price AI coding-agent usage by repo, model, or client. It also supports billing markups, JSON output, and an MCP server for asking agents what their work cost.

A native Mac screen recorder with a built-in editor and MCP support so Claude, ChatGPT, or Cursor can help cut, zoom, add captions, and export demos locally.

Vehla is a native macOS command center with on-device AI, clipboard intelligence, window management, dictation, and local-first workflows. It combines launcher-style actions, clipboard recall, shelves, workspace tools, and model connectivity in one app.

Stroq is a local action firewall for AI coding agents. It scans tool output, marks risky sessions, blocks dangerous follow-up actions, and keeps a hash-chained audit log, with support for Claude Code, Cursor, Codex, Copilot CLI, Windsurf, OpenClaw, and MCP clients.

Open-source agentic workspace for teams that combines apps, chat tools, integrations, models, and agents in one local-first environment with shared memory.

A macOS desktop product for running multiple coding agents in parallel from one workspace, with shared accounts, memory, and skills. The page also highlights Lanes Link, an MCP-based endpoint for connecting agent clients to accounts, context, and access profiles.

A browser extension that lets users move AI chat threads between ChatGPT, Claude, and Gemini without retyping. It supports exporting/importing local .chatbridge files and emphasizes browser-only, local-first handling.

Local-first tool that analyzes Claude Code session logs to explain where usage went, diagnose quota spikes, and generate reports from plain-English questions or slash commands.

Cadre is a local-first Kanban board for orchestrating coding agents, including Claude Code, Codex, Grok, Opencode, and OpenAI-compatible setups. It routes tasks, handles blockers and approvals, and keeps agent runs, diffs, and command control in one workspace.

Local-first coding agent that runs on the user’s machine and can work across the browser, desktop, terminal, and editor surfaces. The repo says it verifies fixes by reproducing failures and re-running assertions, with install instructions for Windows, macOS, and Linux.

Open-source, local-first usage and cost meter for AI coding agents. It reports usage metadata from tools like Claude Code, Codex, Cursor, Grok Build, Hermes, opencode, Cline, and Copilot CLI, with budgets and warnings and no account or telemetry.

Crux is a local-first AI personal assistant for Mac and Windows that works across desktop apps, files, and workflows. The page shows remote access, messaging integrations, and examples like spending analysis, UI edits, and writing tasks.

Open-source local-first agentic IDE for autonomous software development with governed execution, persistent tasks, evidence-backed memory, and multi-environment runtime support.