Tools

MCP server that gives AI coding agents on-demand access to private project docs via BM25 ranked search. One setup for Claude Code, Cursor, Codex, Gemini CLI, and more. Docs stay private, never in public repos.

Custom AI agent platform to speed up your work.

Bichon – A lightweight, high-performance Rust email archiver with WebUI

Open, sub-millisecond, single-executable FireBase alternative with type-safe REST & realtime APIs, built-in JS/TS runtime, auth & admin UI.

The missing context layer for AI-assisted refactoring

A simple, blazingly fast, selfhosted URL shortener with no unnecessary features; written in Rust.

Tool to build & run portable, lightweight, self-contained virtual machines.

ClickHouse® is a real-time analytics database management system

secure, local, cross-platform and programmable sandboxes for AI agents

Stateful MCP server over real language servers. 50 tools, 30 CI-verified languages, 20 agent workflows. Persistent sessions keep the index warm across files and projects. Speculative execution simulates edits in memory before writing to disk.

The software powering Stoat

Open-source webhooks as a service that makes it super easy for API providers to send webhooks.

A command line utility to work with Sentry.

Durable, agent-native AI runtime with native MCP client + server and A2A support. Rust core for performance, Python authoring for ergonomics. Features graph-based workflows, durable execution, and multi-agent coordination.

Fully transparent SSH, HTTPS, Kubernetes, MySQL and Postgres bastion/PAM that doesn't need additional client-side software

All-in-one Mail & Collaboration server. Secure, scalable and fluent in every protocol (IMAP, JMAP, SMTP, CalDAV, CardDAV, WebDAV).

Aggregate results from other search engines (metasearch engine) without ads while keeping privacy and security in mind. It is extremely fast and provides a high level of customization (alternative to SearX)

Web content extraction for AI agents. 10 tools: scrape, crawl, map, batch, extract, summarize, diff, brand, search, research. TLS fingerprinting bypasses anti-bot without a browser. 67% fewer tokens than raw HTML. `npx create-webclaw` auto-configures Claude, Cursor, Windsurf, Codex, OpenCode.

Kanidm: A simple, secure, and fast identity management platform

Parseable is an observability datalake built from first principles.

Selfhostable web app to make managing mTLS certificates a breeze

☁ Ultra-fast, secure & lightweight self-hosted cloud storage — your files, photos, calendars & contacts, all in one place. Built in Rust.

Universal MCP gateway with single-port multiplexing and Meta-MCP. 4 meta-tools replace 100+ registrations, saving 95% context window. Hot-reloadable capabilities, OpenAPI auto-import, 42 starter capabilities (25 zero-config).

Semantic code indexer with GraphRAG knowledge graph. Index your codebase, search in natural language, and expose everything via MCP so AI agents understand architecture — not just files.

Synapse: Matrix homeserver written in Python/Twisted + Rust

Ultra-fast web fetcher and MCP server with HTTP/3, JS rendering, anti-fingerprinting, browser cookie auth, and 1Password integration. Fetches any URL as clean Markdown for AI context.

Scalable datastore for metrics, events, and real-time analytics

Safety guardrails for ai coding agents and human terminal commands

wastebin is a pastebin

Local-first orchestrator that runs inside your existing Claude or Codex CLI via MCP; classifies a request, decomposes it into tickets with a dependency DAG, dispatches across one or more repos, and supervises with live PR tracking + approval gates. CLI, TUI (ratatui), and GUI (Tauri)

AI-native ontology engineering with 39 tools and 5 prompts for OWL/RDF/SPARQL. Validate, query, diff, lint, version, and govern knowledge graphs via Oxigraph triple store.

AI-native calendar middleware for scheduling, availability, and conflict-free booking across Google Calendar, Outlook, and CalDAV. 15 tools across 5 layers: temporal context, calendar operations, multi-calendar availability, open scheduling, and Two-Phase Commit booking. Deterministic datetime resolution and RRULE expansion powered by Truth Engine.

Persistent 4-tier AI memory (episodic, semantic, project, procedural) with temporal scoring, contradiction detection, entity tracking, and real-time desktop visualization orb.

Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concepts, naming conventions, and vocabulary queryable via MCP.