rust

GAN-style self-improvement loop for any text artifact: mutate, grade with a SEPARATE model, keep only verified wins (pairwise-judged), revert the rest. The git history is the improvement log.

Free, open-source offline voice dictation for Windows, macOS, and Linux. A Wispr Flow alternative with an AI assistant that can read your screen on request and answer questions.

High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelligent applications.

High-performance Ollama & LM Studio proxy with per-user fair-share queuing, round-robin scheduling, and a real-time TUI dashboard. Built in Rust.

A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.

🦀 A Pure Rust Framework For Building AGI.

A local-first AI workspace — multi-provider chat, an autonomous coding agent, 3D models, ERPs, and multi-agent swarms in one native desktop app. No backend. No telemetry. No account. MIT-licensed.

The fastest Office document library for Python, Rust, Go, JS/TS, C# and WASM. DOCX, XLSX, PPTX, DOC, XLS, PPT. Up to 100× faster than python-docx/openpyxl/python-pptx. 100% pass rate on valid Office files. MIT/Apache-2.0.

A high-performance AI Gateway written in Rust — call 100+ LLM APIs using OpenAI format

The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLLM/SGLang — 0.76 µs per request, no I/O on the request path, cache-affinity routing, RBAC, budgets and a 13-screen UI in the binary.

Desktop app that auto-detects a game's engine, extracts the text, translates it with local or cloud AI, and re-applies the patch. 20+ engines, 20+ AI providers, 11 UI languages. Free & source-available, single-player focused.

🤖 A prompt manager for MacOS built with Tauri ♉️

A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-device. MLX-native, Ollama/OpenAI API compatible, zero API keys.

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

Stupid Linux Terminal

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

Open-source Mindful Productivity App for macOS

Friendly interface to chat with an Ollama instance.

Linux-first voice-to-text dictation tool for Wayland, X11, Niri, Hyprland & Sway, written in Rust

Production-ready KV-backed HNSW implementation in Rust using LMDB