Discover the Best AI Resources

OpenEnv

Provides Gymnasium-style APIs and tooling to run isolated, networked execution environments for agentic reinforcement learning. Offers async/sync EnvClients, Docker/Kubernetes container providers, a web UI and CLI for scaffolding and deploying environments (Hugging Face Spaces); experimental and evolving.

OpenEnv

Provides a Gymnasium-style API and tooling to create, deploy, and interact with isolated execution environments for agentic RL training. Includes async/sync clients, a web interface, CLI, Docker-based deployment, and Hugging Face Spaces integration.

Tinker Cookbook

Worked examples and reusable abstractions for fine-tuning open LLMs via the Tinker training API: you write the training loop while distributed execution runs remotely. Covers SFT, math/code RL, DPO, three-stage RLHF, distillation, and tool use.

NeuTTS

Runs text-to-speech with instant voice cloning fully on-device, from phones to GPUs. Built on small LLM backbones (120M-360M params) plus a 50Hz neural codec; clones a voice from ~3 seconds of audio across English, Spanish, German, and French.

Voyager

Enhances web AI chat interfaces (Gemini, AI Studio, Claude, ChatGPT) with folder-based conversation organization, timeline navigation, prompt vault, cloud sync, chat export, UI fixes and a plugin engine. Runs as a browser extension and includes cross-site prompt management and Mermaid rendering.

OpenMed

Turns clinical text into structured, de-identified clinical signals—entity extraction and PII de-identification—that run entirely on local hardware. Provides 1,000+ specialized medical NER models, multilingual support, Apple MLX acceleration, and Apache‑2.0 licensing.

Cybersecurity Defense Instruction-Tuning Dataset (Fenrir v2.1)

Provides 99,870 system/user/assistant chat triples for defensive cybersecurity instruction‑tuning, with built‑in refusal patterns and mapping to OWASP, MITRE ATT&CK, NIST, and CIS standards; Apache‑2.0 licensed.

Enforces a brainstorm → plan → test-driven → review workflow on AI coding agents instead of letting them jump straight to code. Ships as composable skills that auto-trigger by context and run across Claude Code, Cursor, Copilot CLI, Gemini and more.

Compound Engineering Plugin

Packages Every's 'compound engineering' workflow into 26 slash commands for AI coding agents like Claude Code — brainstorm, plan, work, review, debug. Skews effort toward planning and review, and saves each run's lessons so the next task is easier.

DeepAnalyze

Autonomously performs end-to-end data science tasks — from cleaning and exploration to modeling, visualization, and analyst-grade reports — via an agentic LLM. Open-source model, code, datasets and demos; supports vLLM deployment, Jupyter/CLI/Web UIs, and OpenAI-style APIs.

Beads

Provides a persistent, dependency-aware structured memory for coding agents — replacing scattered markdown plans with a versioned task/issue graph backed by Dolt. Agent-optimized features include JSON output, dependency tracking, zero-conflict IDs, and semantic compaction for long-horizon workflows.

Beads (bd)

A dependency-aware issue tracker for AI coding agents that stores tasks as a version-controlled graph in a Dolt database, so agents keep context across long-horizon work. Content-hash IDs prevent merge conflicts when multiple agents edit in parallel.