#llm

Continuously Looping Engineering Machines. docker-compose for Claude Code agents - persistent teams, 24/7, on any Linux host.

No repository description published.

A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.

Selects and Rotates Models

No repository description published.

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

Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)

Millisecond microVM sandbox forking for AI agents on Kubernetes. Firecracker VMs that restore from memory snapshots in milliseconds, fork a running VM into N copies, and persist durable, versioned workspaces. Self-hostable, declarative CRDs.

LLM-managed personal knowledge base. Auto-extracts from git repos, Claude Code sessions (via ccrider FTS5), and iMessage bookmarks. Cross-project, qmd-indexed, runs on cron

Private, self-hosted AI agent — your models and data stay on your machine. A feature-rich coding + assistant toolset across eight interfaces (CLI, Web, desktop, IM, VS Code, Obsidian, SDK, Mobile), all in one fast, zero-dependency Go binary.

Shared memory for AI agents

Persistent memory for AI agents

Convert PDF documents to Markdown using Vision Language Models — CLI and library

The repo map your coding agent is forced to use — ~98% fewer tokens (up to 99.9% per task) to understand a TS/JS codebase. PageRank hubs, Aider-style symbol ranking, token-budgeted digest, --any router, wired into the agent loop.

OpenAI platform bridge for Symfony AI

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.

Asset-Aware MCP Server — AI Agent precisely accesses tables, figures, sections from PDFs + .docx round-trip editing (DFM) with 46 tools / 13 resources, segmentation export, layout overlay, OCR preprocessing, knowledge graph (LightRAG)

Profile PyTorch models for FLOPs and parameters, helping to evaluate computational efficiency and memory usage.

Whale — blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows.

TypeScript SDK for BlockRun — 41+ AI models, pay-per-call with USDC. OpenAI-compatible. Zero rate limits.

A declarative language that compiles to professional SVG floor plans — like Typst/LaTeX, but for architecture. Built for AI agents: deterministic output, JSON diagnostics that carry their own fix, and a describe/lint channel that verifies a plan against its brief without rendering an image. Zero-dependency TypeScript.

Open, self-hostable agentic runtime for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed sandboxes or on your own hardware. Apache-2.0.

Go SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.

High performance, real-time markdown renderer for AI/LLM

MCP C++ SDK - Model Context Protocol implementation in CPP with enterprise-grade security, observability and connectivity.

A Go toolkit for building AI agents and applications across multiple providers. Unified LLM client, agent framework with handoffs, tool calling, streaming, structured output, MCP integration, and cost tracking.

Constitutional AI Agent Framework with cryptographic identity (DIDs)

Use Web AI as an agent without an API key. $0 | litellm , local models via Ollama, /lang in 34 languages, Mesa Redonda, voice, OCR, MemPalace, embedded sandbox OS. (The Hermes Killer)

🚀 AI-powered code review tool for GitHub, GitLab, Bitbucket Cloud, Bitbucket Server, Azure DevOps and Gitea — built with LLMs like OpenAI, Claude, Gemini, Ollama, Bedrock, OpenRouter and Azure OpenAI

The agent framework where every run is durable, replayable, and resumable by default.