#llm

Self-hosted AI knowledge agent — TypeScript, Bun, MCP. Own your data, run your own brain.

Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.

MCP server + CLI giving AI agents 50 spreadsheet tools for .xlsx — live-recalc formulas (~390 Excel functions), repair broken references & external links, read/write, diff, and audit. Works in Claude Code, Cursor, Codex, and any MCP client.

AI SDK for building AI-powered applications in Go

Agent workflows with full observability and time travel: watch every step live, rewind, fork, replay any run. Claude Code, Codex, Gemini, any model or harness.

AWS Bedrock platform bridge for Symfony AI

Git-native AI agent co-harness — MCP server, static guards, and agentic evaluator for LLM-assisted coding

Yet Another Agent SDK, CLI, Claw, Agent Platform

Tracks which agent wrote which lines when multiple AI agents share one Git checkout.

Use any AI model, locally or in the cloud, while tracking on-device token usage and collecting token telemetry data.

the trust layer for agent memory

A library and SDK to redact sensitive content from GenAI/LLM telemetry (prompts, completions, tool arguments) before it reaches observability backends. Supports OpenTelemetry conventions.

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

🧯 Kubernetes coverage for fault awareness and recovery, works for any LLMOps, MLOps, AI workloads.

Smart hands for your AI agents — write-capable, multi-plane (KVM + BMC + SSH) MCP server for bare-metal control (PiKVM/GLKVM, Redfish/IPMI BMCs): gated, verified, audited. Beta: seeking hardware reports.

ReplyPilot is a TypeScript CLI for automating WhatsApp replies with LM Studio, Ollama, or any OpenAI-compatible chat completions endpoint.

Anti-hallucination AI agent kit for Cursor, Windsurf & Antigravity. 27 specialist agents, 17 slash commands, 8 Tribunal reviewers. Install: npx tribunal-kit init

该仓库未发布描述。

Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Solutions to conduct Agentic RAG from actively selected GitHub public projects. It Augments through LLMs and Generates context for any coding question, in order to streamline the development of sophisticated AI-driven applications.

aindy-runtime is a self-hostable AI agent execution runtime. It provides the infrastructure layer for building and operating AI-powered systems: a syscall-based execution contract, a DAG flow engine, persistent vector memory, structured agent runs with approval gates, and an extensible plugin architecture for mounting domain-specific app layers.

Easiest way to give context to LLMs; Attachments has the ambition to be the general funnel for any files to be transformed into images+text for large language models context by only adding 2 lines to your python code.

Salesforce Org Intelligence for AI agents - a read-only, offline, source-available MCP server and CLI answering metadata, dependency, permission, Apex and Flow questions grounded in real retrieved org metadata.

Management environment Java、Maven、Claude Code

Python SDK for astrology, Vedic kundli, tarot, numerology, horoscope, I Ching, biorhythm and more. One multi domain API key, sync and async. AI agent and MCP ready.

Multi-tier AI orchestration CLI — built for developers who think in systems.

Chat applications that use DAG to build question-answer relationships.

Pull, push, pack, and serve GGUF models as OCI ModelPack artifacts — daemonless, air-gap-first, one binary

Persistent memory & RAG engine for AI agents — SQLite + FTS5 + embeddings, multi-stage recall, sleep maintenance, multi-host hooks

fak — the Fused Agent Kernel: one Go binary for AI agent loops. Wrap Claude Code/Codex/Cursor, keep long sessions cache-efficient, route work per call, run local GGUF models, and adjudicate tool calls.

Multi-objective bandit routing with drift detection