1Password for coding agents: find, use, and save secrets without exposing them

Run one-time deployment operations in Laravel.

An audio server, programming language, and IDE for sound synthesis and algorithmic composition.

Open-source personal AI agents that work on their own, on their own computers. Mac app, OpenAI + Composio.

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

Full named-entity (i.e., not tag/token) evaluation metrics based on SemEval’13

Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollama for decision models.

Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

A small, fast WebKit browser for macOS, by Office Commun.

A brain that learns from live experience. System 1 by default: perception, memory, plasticity and action. Optional System 2 for self-observation and slow corrections.

The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.

Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST API and MCP support for AI clients.

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

A local inference engine for Apple silicon, built around the model.

A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.

Fastest and cheapest web agent

Research & training for DataFog's next-generation PII detection model

MITM proxy for Claude Code with real-time TUI, web UI & MCP server — intercept, inspect, and send messages to the Anthropic API. Headless mode for automation.

Privacy proxy for your OpenAI requests

A collection of resources for PII detection, anonymization, privacy-preserving techniques, and GDPR compliance in Large Language Model (LLM) or AI applications.

Beautiful pdf components, built on Takumi and Forme. 100% Free, Zero config, one command setup.

Agent skill for impressive 3D visuals using Blender + image gen + subagent critic

modular service framework to move and transform network packets

Autonomous research system for measurable, computer-executable research.

The simplest, thinnest harness that gives an LLM complete freedom to control a Mac.

The coding agent that answers to you, your model, your machine, your rules.