Fast, accurate & comprehensive text measurement & layout

Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.

Token-efficient autonomous task execution with context collapse for pi coding agent

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

Experimental Linux microvm setup with a TypeScript Control Plane as Agent Sandbox

The open-source app everyone uses to manage agents at work

A local, git-worktree multi-agent swarm orchestrator for Codex, Claude, Gemini, and OpenCode

A curated list of awesome things related to the WebMCP proposal

Hi this is Mercury

Fetch an entire site and save it as a text file (to be used with AI models).

Skills for pi coding agent (compatible with Claude Code and Codex CLI)

Fractals is a recursive task orchestrator for agent swarm

Hooking implementations and supporting tools for various coding agents (Claude, Cursor, Gemini, etc)

A BaaS (Backend-as-a-Service) solution for web applications, inspired by the flexible nature of triplestores. Featuring real-time collaboration and serverless authorization 🔐

Build immersive AR and interactive 3D. Free and open.

Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining Tree-sitter AST parsing, Spectral Clustering, and Obsidian…

MCP server paired with a browser extension that enables AI agents to control the user's browser.

Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser

CReact is how you write your workflows using JSX, build durable apps that you can sync with external state, build jobs, agents, infastructure, anything you can declare you can build!

Runs 405B LLMs on 8GB VRAM

A minimal, file‑based agent loop for autonomous coding.

Like Prometheus, but for logs.

💬 A proposal for a web API for prompting browser-provided language models

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS ev…

Liquid Audio - Speech-to-Speech audio models by Liquid AI

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

General-purpose AI designed for knowledge workers — creators, strategists, and operators — and individuals seeking AI systems they can truly control to help them get work done, with full flexibilit…

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs