#anthropic

Persistent memory, architectural decision enforcement, pre-execution safety hooks, and session handoff for Claude Code. MCP server plugin for AI coding agents.

Measure Claude Code and Codex usage. Get your Professional AI Usage Index, run-rate, tier, and verified shareable rank.

Validate Claude Code plugin manifests before submission. Go CLI + GitHub Action that catches reserved marketplace names, duplicate hooks declarations, path traversal, and schema errors the official validator reports opaquely. roninforge.org/hanko

Copilot SDK for building Production-ready AI Copilots for any product. Connect any LLM, deploy on your infrastructure, own your data. Built for speed and control.

Production-ready AI Business OS — 46 autonomous AI Employees, Graph RAG (Neo4j), multi-channel, BYOK across 17 LLM providers plus custom/local endpoints (Ollama), automatic fallback. 8 libs (Python+Java). Self-hosted, MIT licensed, guardrailed autonomy for regulated industries.

local-first analytics for AI agent skills

The verification layer for LLM serving — your check runs on every answer before it ships, with a signed, tamper-evident receipt for each decision and a distribution-free bound on wrong answers served. Proof over prediction.

Open-source financial accountability for AI-agent work. Connect Claude Code and Codex activity to cost evidence, attribution, runway, and evidence-backed next actions via CLI or MCP; customize the source-built macOS Glance. Local transcript analysis stays on your machine.

Dual-provider LLM gateway (OpenAI + Anthropic) with an agentic tool-use loop over milpa/tool-runtime. Apache-2.0.

AI 能力底座 — 统一 LLM Provider 接口（OpenAI/Anthropic/DeepSeek/Gemini/Ollama），图片生成，视频生成，Embedding，向量存储，记忆管理。Hexagon 生态 L1。

Run multiple Claude Code accounts as one. Auto-switches on rate limits and resumes your session no lost context, no logout dance.

Uniform streaming LLM interface for voice agents — OpenAI, Anthropic, Google, Vertex, Bedrock

Python SDK for m8tes — give every customer their own AI agent through one API. Hosted runtime, 150+ integrations, scheduling, memory, human-in-the-loop.

El repositorio no publica descripción.

Loom is a high-performance, graph-based AI workflow engine for Go. It allows you to build complex agentic systems by defining multi-step workflows as directed graphs, seamlessly connecting them to any large language model, and persisting execution state for long-running or interrupted tasks.

The state layer for LLM agents: durable conversations, agent-curated memory, skills, a shared board and a ledger of who did what — on storage you own.

Rust interfaces to the streaming code protocols.

TypeScript harness for building personal AI agents with durable memory — agents that live across your channels (CLI, Teams, iMessage, mail, voice), use real tools, and stay coherent across turns. The runtime behind @ouro.bot.

Universal Agent Harness from Happy that works with any subscription

PHP LLM client with support for cache, tools and async requests

El repositorio no publica descripción.

Adaptive fork of Pi coding agent for self-evolving agent harness experiments

A local-first, self-evolving terminal AI coding agent based on Pi — reads, edits, and runs code through conversation, and improves its own prompts and skills over time.

CLI for Goodeye: turn business outcomes into verified AI workflows that agents run reliably.

El repositorio no publica descripción.

Inspectable, source-traceable public-equity research for Codex, Claude Code, OpenCode, Grok Build and ChatGPT Work developer mode. 26 provisional method lenses, 34 MCP tools. Research software, not investment advice.

Model-agnostic agent harness for Elixir

A skill system for Laravel AI SDK agents. Define reusable AI capabilities with SKILL.md files.

Coordination-free client loadbalancer for Azure Foundry

Provider-agnostic GenAI client for Laravel: Gemini, AWS Bedrock, and more