#llm

The Open Agent Operation System

AI Financial Governance SDK — every LLM call is a double-entry transaction

MCP server with 40 tools for AI agents. Memory, web fetch, search, file ops, screenshots, and multi-agent coordination in one Go binary.

The coordination layer for hybrid distributed AI compute.

MCP server for the GitLab REST API — 91 tools, 7 resources, 6 prompts for projects, MRs, draft reviews, repository files, pipelines, CI/CD, approvals and issues. MCP 2026-07-28 (MCP 2.0); GitLab.com and self-managed; read-only mode, OAuth 2.1 and local sign-in.

♾️ Umbrella php package and unified CLI for the governed agentic-coding loop: board (kanban), learning, and recall-compiler.

Método de agência orientado por IA, em PT-BR. Um maestro lê seu pedido e chama o agente certo. Fork independente do BMad Method.

yeaboi — AI Scrum Master in your terminal: sprint planning, standups, retros, planning poker, 1:1s and delivery reports for your team, plus cost, daily digests and security posture for the AI coding agents working alongside it.

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.

Strip common prompt injection surfaces.

Django ↔ Pydantic-AI ↔ AG-UI integration: an AG-UI agent endpoint with a pluggable tool registry.

CPersona — persistent memory for AI agents over MCP. One SQLite file you own, hybrid vector + full-text + keyword search, no LLM in the loop, and honest reporting when recall degrades. MIT licensed.

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

Fault-injection toolkit for testing the resilience of LLM calls and agentic workflows.

Memory security for AI agents. Scan native memory writes, gate tools on bound hosts, inspect what was stored. Not a second brain.

Hexalith Memory Module with syntactic and semantic search

Jiva is a CLI-first, open source autonomous AI agent and open alternative to Claude. Written in TypeScript with native support for Sarvam-105B and gpt-oss-120b, it autonomously plans and executes tasks from your terminal. Supports MCP servers, a built-in Skills system, and Jiva Personas - a plugin framework fully compatible with Claude Plugins.

A Javascript SDK for the Linkup API

Self-hosted runtime for AI agents and workflows. Durable execution, capability-gated tools, human approval gates, and a memory system that accumulates. Runs survive restarts and resume where they stopped. Mount your domain logic as a plugin package or drive it over the HTTP SDK

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 20 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

Open-source framework for deploying conversational AI agents that capture customer intelligence at every touchpoint

Know what breaks before you change Salesforce. Ask your AI about your org: where a field is used, what runs on save, which Apex is dead, who can see what. Offline, read-only, cited. Open source (MIT).

Universal LLM bridge for AI agents. Use Claude Code with MiniMax, Codex with GLM, or Gemini CLI with OpenRouter — one command, any provider. Works with coding agents, OpenClaw, Hermes, and others.

Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.

A production-grade agent runtime engineered from the Harness Engineering philosophy.

Terminal49 Developer Platform - Global Shipment and Container Tracking.

该仓库未发布描述。

Typed Go SDK for bounded AI agent loops, tool calling, subagents, orchestration, and optional durable execution.

MCP that delegates mechanical text tasks to a local OpenAI-compatible LLM endpoint to conserve Claude subscription quota.

A fast, AST-based code navigation toolkit that maps file shapes, public APIs, and call graphs across coding languages. Designed to help coding agents and humans explore codebases, analyze blast radius, and generate token-budgeted context with massive token savings.