#local-first

Compiles a demonstrated GUI task into a program that reports VERIFIED only if an independent check agrees. pip install openadapt; openadapt flow tutorial. Compiler lives in openadapt-flow.

Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.

Project Management for the agent era

Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboard, no account required with a generous free cloud plan

Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.

Make your JSON data collaborative and version-controlled with CRDTs

A pure-Go, production-grade implementation of Yjs. Runs real collaborative apps: a horizontally-scaling, Hocuspocus-compatible websocket server with versioned persistence and compaction. Hardened by differential fuzzing and a byte-level conformance suite. Also embeddable on iOS/Android via gomobile.

A reactive data store & sync engine.

Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.

All the things a panda needs

Lightweight orchestration harness built for your AI agents. The unfiltered truth about where your project stands.

Stop feeding broken Markdown to your AI. A deterministic Logseq parser that preserves parent-child context for RAG, plus a 60FPS visualizer 👓 , plus writer ✍️ append only

Safe DOCX suite: docx-primitives, docx-comparison, safe-docx MCP server

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Cursor & any MCP client: Markdown source of truth, hybrid search (MLX/CPU + sqlite-vec), time-machine, contradiction radar, nightly self-optimization. No cloud, no keys.

Self-hosted memory + evidence layer for AI agents (Claude Code, Codex, Hermes, ...) — embeddable Go library, MCP / HTTP / CLI, evidence-backed claims, bitemporal recall, axi-go execution kernel with JSONL audit + token budgets, cosign-signed releases with SLSA L3 provenance. No vendor cloud, no per-call billing.

Stop letting your work go unnoticed. Meridian keeps an automatic work journal of what you worked on and what you finished, summarised daily, and automatically drafts your project tickets for you.

The decision layer for personal AI. Local-first runtime where agents automate across GitHub, Slack, Gmail & 45+ services — but every risky action can stop for your yes, workers (agents) earn autonomy from track record, and every decision leaves a receipt. Your models, your machine, your policy. Includes an MCP bridge: 180 IDE tools for Claude Code.