Explore the directory

Loads an unpacked Chrome extension that lets a local AI coding agent click, type and read the tabs, cookies and logins of a Chrome window you already have open.

• Coding agents
• Browser automation

Reads an existing docker compose file and deploys it as a remote preview environment with little setup, with optional public endpoints and authentication so others can review in-flight work.

• Containers
• Hosting

A CI/CD platform that auto-compiles existing APIs into Go MCP servers, attaches composable middleware, and exposes them through one gateway usable from Cursor, Claude Code, and Windsurf.

• MCP servers
• CI/CD

A no-backend browser client for a local Ollaya decision server: build typed questions, get calibrated probability answers, and manage the server's local models.

• Inference

A browser tool that mixes, stretches, and squishes two fonts together glyph by glyph, exporting the result as a downloadable TTF, OTF, or WOFF2 web font.

• Design tools

A SQL-first data-access toolkit for TypeScript that keeps ordinary SQL visible in tagged template literals, binds interpolated values safely by default, supports readable conditional SQL directives, and lets a schema validate the returned rows.

• Libraries
• Databases

A command-line tool for toggling a system-wide collection of MCP servers on and off, globally or per project, so a rarely needed server can stay out of an agent's context by default and be enabled only when it is actually wanted.

• MCP servers
• CLI tools

A tool that gives AI agents temporary, auditable access to a machine, replacing standing SSH keys with session-scoped permissions and full audit logs.

• Security
• Auth

A technical article showing how to call TypeSafe.ai's Jev decision model from a TanStack Start server route through TanStack AI's Vercel AI Gateway adapter to build a typed routing endpoint.

• Tutorials

A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

• Agent frameworks

A macOS app that gives coding agents such as Claude Code a persistent visual workspace, so an agent can build interactive pages, tools, and diagrams that stay wired to the underlying repo.

• Coding agents
• Debugging

An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

• Agent frameworks

A tool that connects two AI coding agents directly over an encrypted peer-to-peer link, so they can compare notes, agree on an interface, or debug together without a human relaying messages.

• Coding agents

An open-source desktop app from CodePawl for running a small team of named AI workers on your own computer, using the Claude Code, Codex, Cursor, or Gemini CLI plan you already pay for.

• Coding agents

A Swift package that answers multiple-choice, graded and yes/no questions about a piece of text using an on-device language model on Apple Core AI, returning a probability for each possible answer, inspired by TypeSafe's Jev.

• Inference
• Libraries

A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

• Agent memory

Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.

• Coding agents
• Agent frameworks

A co-evolutionary adversarial red-teaming tool for AI agents that uses quality-diversity evolutionary search to autonomously breed edge-case scenarios, testing whether an agent with tool access can be made to hallucinate, deadlock or leak funds.

• AI evals
• Security

A free, open-source macOS menu-bar app that finds the dev servers, builds and MCP server copies that coding agents such as Claude Code and Codex leave running, measuring each process's real memory footprint including what has been swapped out.

• Coding agents
• Desktop utilities

An independent implementation of TypeSafe's Jev wire format that adds typed, probability-scored multiple-choice, graded and yes/no questions on top of any OpenAI-compatible client, reading logprobs where a provider exposes them.

• Inference
• Libraries

Evaluations and guardrails for AI agents that replace an LLM-as-judge with typed decision models, scoring every metric for a trace in one request that costs a fraction of a cent and returns in a few hundred milliseconds.

• AI evals

A Windows UI Automation backend for computer-use agents that clicks, types and navigates real Windows applications through a fast, structured decision loop instead of a screenshot-and-guess approach, so a frontier model is not needed for every click.

• Agent frameworks

An agent-first screenshot API that captures a hosted, pixel-perfect image of any URL through a one-line CLI, a hosted MCP server, or a plain REST call.

• MCP servers
• APIs

An independent testing service, backed by Y Combinator, that runs an application and tries to break every change an AI coding agent makes, reporting what would have reached production.

• Testing