#llm

TokenSpeed is a speed-of-light LLM inference engine.

A multi-agent framework written in Rust that enables you to build, deploy, and coordinate multiple intelligent agents

Runtime security and governance for MCP servers. One gateway, full visibility, policy enforcement - from dev laptop to production fleet.

Short-term memory proxy gateway with proactive memory surfacing for AI agents

A typescript library for connecting videos in your Mux account to multi-modal LLMs.

Self-hostable, MIT Licensed, Enterprise AI Software Factory

Governance substrate for your AI coding agents — adversarial review, drift-detected rules, immutable audit, closed-loop telemetry

TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML

Autonomous AI agent for Home Assistant with multi-model routing, persistent memory, and an OpenAI-compatible API

The Best AI Agent Framework for Agent Collaboration.

Fast KV-cache quantization for Apple Silicon (MLX) — 43 research-adapted compression methods with Metal kernels

MCP budget and risk authority for Cycles — runtime governance for Claude, Cursor, and Windsurf

Parse bank statements — CAMT/ISO 20022, PAIN.001, CSV (EN/DE/FR/ES), OFX/QFX, MT940, PDFs (digital + scanned) — into unified Transactions. Deterministic parsers, LLM/vision fallback, Golden Rule + multi-currency + continuity verification, page provenance, dedupe, review, accuracy evals, CLI + REST API. 100% test coverage.

Your feedback loop with the agent

No repository description published.

Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time

MCP server providing unified access to Claude Code, Codex, Gemini, Grok and Mistral CLIs with session management, retry logic, and async job orchestration.

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics

Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operations platform (AI SOC)

Enterprise-ready self-hosted AI assistant runtime with sandboxed execution, secure credentials, approvals, and memory

One endpoint in front of unlimited MCP servers and REST APIs. The agent sees a fixed ~15-tool surface however many you connect, so tool-list token cost stays flat (about 89% less on a 100-tool stack) and the savings climb as you add more. Single Rust binary.

Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, task-aware desktop pets, with WeChat, Feishu, DingTalk, Telegram, WhatsApp and H5 access.

Agentic business runtime — Users, Content, Products, Payments, Intelligence. Build your business, not your boilerplate.

An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, and a browser UI, while you keep your hand on every permission.

Local MCP server that exposes eBay Sell APIs to AI assistants with OAuth, tool gating, and stdio/HTTP transports.

AI integration layer for Jido agents with LLM orchestration and reasoning strategies.

LLM model metadata catalog with fast, capability-aware lookups

LLM model metadata catalog with fast, capability-aware lookups