Search

Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

Eval framework for agent skills, across Claude Code, Codex CLI, Copilot CLI and OpenCode

950+ API connectors for AI agents: catalogue, auth requirements and connection management, sync and async

VCR cassettes for agent trajectories: record agent runs as DAGs, replay the canonical path, only call the LLM for net-new paths.

Framework-agnostic AI/LangChain engine: OpenAI/Anthropic/Bedrock chat models, Pydantic structured outputs, tool-calling agents, and pure cost calculators.

CrewAI tool integration for Attestify — governed AI loop execution, receipts, and audit trails

AutoGen tool integration for Attestify — governed AI loop execution, receipts, and audit trails

LangChain toolkit for Attestify — governed AI loop execution, receipts, and audit trails

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM providers.

⚡ Advanced AI iteration framework featuring an 8-stage pipeline, automated fine-tuning, voice interaction, and security scanning.

AI accounting agent for Polish SMBs: LangGraph agent with 80+ domain tools over wFirma, KSeF e-invoicing (FA-3), e-Doręczenia inbox watcher, and a statutory tax calendar with proactive deadline reminders. TypeScript monorepo — Next.js 15 web + Express/Prisma API, Telegram bot, voice chat, Stripe billing.

Open-source alternative to LangGraph Platform for TypeScript — self-host your LangGraph.js agents behind the standard Agent Protocol API. Your infra, your Postgres, no vendor lock-in. Drop-in for the LangGraph CLI.

Agente autónomo para LALIGA Fantasy: lee el juego, decide y actúa (pujas, ventas, clausulazos, alineación). Python stdlib + agente LLM opcional (Hermes) + UI de supervisión.

铁锈战争单机 LLM 指挥链：javaagent 实时取数 + Python 分层多 agent 决策（纯单机研究项目，严禁用于多人对战）

LangChain tools for Arbiter — pre-flight judgment for agents that hold a wallet.

Shared, consistent permission-prompt and policy layer for AI coding agent tools

Multi-agent orchestration for Pi: autonomous subagents, worktrees, swarms, schedules, handoffs, prompt compression, and live TUI observability.

Local-first, private long-term memory for AI agents. Everything runs on your machine — data never leaves your disk. Backed by LanceDB and Ollama embeddings

Personal AI agent conventions - installs shared guidelines into a repo's CLAUDE.md (Claude Code) and AGENTS.md (Codex, Cursor) from a single source of truth.

Fast, type-safe image and video compression for Node.js — parallel by default, with a colorful CLI and machine-readable JSON output for AI agents.