Category

camofox-browser

Provides a REST server that lets AI agents browse sites while avoiding common bot-detection by running Camoufox (a Firefox fork with C++-level fingerprint spoofing). Returns compact accessibility snapshots, stable element refs, session isolation, proxy/geoIP support, and agent-friendly endpoints (click, type, snapshot, transcripts).

OpenViking

Models an AI agent's context as a file system, unifying memory, resources, and skills instead of flat vector RAG. Uses L0/L1/L2 tiered loading to cut tokens, directory-recursive plus semantic retrieval, and visualized retrieval traces for debugging.

ATLAS — Adaptive Test-time Learning and Autonomous Specialization

Self-hosted coding assistant that runs frozen local LLMs with constraint-driven planning, energy-based verification, and self-verified repair to produce verified code. Emphasizes offline inference (no cloud), Docker/bare-metal deployment, and requires a 16GB+ GPU.

Microsoft eXecution Container (MXC)

Runs untrusted code (LLM outputs, plugins, and third‑party tools) inside cross‑platform, policy‑driven sandboxes. Provides a unified JSON schema and a TypeScript SDK that sit on multiple containment backends (process sandboxes, LXC/Bubblewrap, microVMs). Early preview with known permissive profiles — not yet a security boundary.

pdf-inspector

Rust library for fast PDF classification and position-aware text extraction that converts native-text PDFs to structured Markdown without OCR. Offers per-page OCR routing, multi-column and table detection, and Python/Node.js/WebAssembly bindings for low-latency local pipelines.

executor

Local integration layer that lets AI agents discover and securely call OpenAPI, MCP, GraphQL, or custom JavaScript functions. Centralizes a shared tool catalog, auth, and policy surface across multiple agents, with a local web UI and CLI for runtime control.

LiteParse

A fast, local document parser that extracts spatial text with bounding boxes from PDFs and other formats. Bundles Tesseract OCR and supports HTTP OCR servers, multi-language bindings (Rust, Node, Python, WASM) and screenshot generation; best for lightweight local pipelines but less suited to very complex or heavily scanned documents.

OmniRoute

Acts as an OpenAI‑compatible local and cloud gateway that routes requests across 100+ LLM providers with smart routing, load balancing, retries and fallbacks. Adds policies, rate limits, semantic caching and observability for reliable, cost‑aware inference in Docker, Electron or npm installs.

llmfit

Detects your machine's CPU/RAM/GPU and ranks which LLMs will run well: estimates memory fit, speed, quality, and context, offers an interactive TUI and CLI, and lets you run and share reproducible local benchmarks.

forge

Provides a reliability layer for self-hosted LLM tool-calling and multi-step agent workflows. Adds guardrails — rescue parsing, response validation, retry nudges, and a synthetic respond tool — and ships a Drop-in OpenAI-compatible proxy plus a WorkflowRunner for structured loops.

CloakBrowser

A Chromium binary patched at the C++ level to evade bot-detection and serve as a drop-in Playwright/Puppeteer replacement. Notable features: source-level fingerprint patches, human-like input emulation, auto-updating binaries, and integrations for Python/Node.js and Docker — useful for scraping, agent-driven browsing, and stealth automation.

Rapid-MLX

Runs local AI models on Apple Silicon as an OpenAI‑compatible server, emphasizing low latency, prompt caching, and reliable tool-calling. Optimized for M1–M4 Macs with multimodal support and drop‑in compatibility for IDEs and agent frameworks.