Search

Track token usage across 22 AI coding tools (Claude Code, Codex, Cursor, Gemini, Roo Code, Zed Agent, Goose, and more) — local-first, zero-config, with a beautiful dashboard, native macOS menu bar app, and 4 desktop widgets.

A setup guide for private equity and CRE GPs to build governed AI workflows for recurring deal, investor, and fund work — without replacing systems of record or giving a model free run of firm data.

openma - open-source, self-hosted implementation of Claude's Managed Agents API. Drop-in compatible. Runs on Cloudflare Workers + Durable Objects or Node. Apache 2.0.

A Go framework for the microagents architecture with dynamic discovery — specialized agents and tools that register their capabilities with a shared registry, find each other by logical name at runtime, and coordinate without a central conductor.

Async-first Python runtime for building provider-agnostic LLM, agent, tool-calling, streaming, caching, and structured-output workflows across OpenAI, Anthropic, and Google Gemini.

An AI-powered automated benchmark team designed to dynamically generate accurate dataset test-suites and automatically evaluate multiple LLM models (GPT-4.1, GPT-4o, GPT-4o-mini) simultaneously.

Multimodal AI testing agent for Web apps: Qwen-VL screenshot/video analysis, DeepSeek review, bug localization, log/code analysis, and pytest/Playwright test generation.

Windows desktop operator powered by Codex App Server

MCP server + LangGraph agent for analyzing FDA-style clinical trial protocols. Exposes 4 tools to Claude Code for entity extraction, adverse-event clustering, and summarization. FastAPI, Pandas ETL, AWS-ready Docker.

Static + runtime linter for LLM agent prompts, skills, and tool definitions. Model-aware policy for Claude, GPT, OpenRouter.

A lightweight LLM agent framework supporting async OpenAI and Anthropic APIs with ReAct agents, TODO-based agents, and built-in tools

Portable task-to-code pipeline that works with any LLM. Turn a one-line task into a verified code change — diff + test + verify loop. +54 pts on a 156-check benchmark vs raw prompting.

PostgreSQL storage backend plugin for the Orchid AI framework

ChromaDB vector-backend plugin for the Orchid AI framework

Anchor-addressed DOCX editing for LLM agents — a thin client over Docxodus' DocxSession.

FortifyOS runtime protection for LangChain and LangGraph agents — zero code changes required.

Multi-provider LLM agent with an interactive REPL

Repo-specific drift monitoring for AI-agent runs.

Template repository for custom AI agent skills with a multi-platform terminal installer (Cursor, Claude Code, Codex, OpenCode, Pi).

CLI to install AI agents, skills, and CLAUDE.md files across a multi-project workspace