#ai

Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, outputs, and tools — the model handles its own control flow. Get fully interpretable trajectories and performance that scales directly with model improvements. Without context rot.

Our vision is to provide communication capabilities for intelligent agents, allowing them to connect with each other to form a collaborative network of intelligent agents.

A secure JavaScript sandbox designed for safe AI agent code execution. Protects against code injection, prototype pollution, and sandbox escapes. The security layer that makes AI-generated code safe to run.

A Model Context Protocol (MCP) server that enables AI assistants to interact with Anki, the spaced repetition flashcard application.

Spec-first AI development: describe a feature → AI creates spec + plan + tasks, builds autonomously, syncs to GitHub/JIRA. Domain-expert skills for PM, Architect, Frontend, QA learn your patterns permanently. Claude Code, Codex, Cursor, Copilot & more.

SciRS2 - Scientific Computing and AI in Rust., providing SciPy-compatible APIs while leveraging Rust's performance, safety, and concurrency features. Unlike traditional scientific libraries

Maya-specific implementation of Model Context Protocol (MCP) for Autodesk Maya, enabling remote control and integration with MCP ecosystem.

Persistent memory for AI coding agents. Your agent learns your codebase the way a senior engineer would — what files go together, what you usually edit next. Works with Claude Code, Cursor, Cline, Continue. 100% local. (Side effect: 40-70× cheaper code questions.)

Collaboration infrastructure for AI coding agents | AI 编程代理的协作基础设施

Multi-Provider AI Gateway - No personal logs by design. Model autodiscovery, Failover groups, High availabilty, Android companion app, and more. "Because we have LiteLLM at home"

Rust bindings for OpenNMT/CTranslate2

Tower-native Model Context Protocol (MCP) implementation

Turn your phone into a remote control for AI coding sessions running on your dev machine.

Privacy-first web interface for local AI models. Clean, minimal UI for Ollama with extensible plugin system. No data leaves your device.

The .NET library to build AI agents with 30+ built-in connectors.

Universal memory runtime for AI agents

KIT (Knowledge Inference Tool) — A lightweight AI agent for coding

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

Local, BYOK code review for any language. No SaaS, no telemetry.

A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.

该仓库未发布描述。

A powerful Model Context Protocol (MCP) server for IMAP email integration with Claude

Automatic create changelog with AI. 🤖 It provides CLI and github actions. 🚀 https://www.npmjs.com/package/@nyaomaru/changelog-bot

agent multiplexer that lives in your terminal.

Kubernetes operator for managing Paperclip instances - the open-source AI agent orchestration platform

Ruby's capable AI runtime

RushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.

Build interactive AI agents in Elixir with OTP supervision, middleware composition, human-in-the-loop approvals, sub-agent delegation, and real-time Phoenix LiveView integration. Built on LangChain.

Run AI coding agents (Claude, Codex, Gemini …) unattended — auto-answer prompts, auto-retry on rate limits, and list/tail/steer every agent locally or from agent-yes.com

The Whisper_CTranslate2 Windows executable, updated daily