#llm

A governed agent SDK for TypeScript - cost budgets, tamper-evident audit, and PII redaction built into the loop.

A CLI that orchestrates headless coding agents (Claude, Codex, Gemini, and more) into supervisor, relay, solo, and adversarial review workflows with inspectable run artifacts.

LLM Simulation for Load Testing

Mission working memory for LLMs: named session graph (GQL) — cue, bounded pin_map, gated mutate. Not chat SSOT, not RAG/GraphRAG, not a DB proxy.

World's first compiler and execution platform for AI systems — turn prompts, skills, and multi-step agent workflows into versioned, packageable software that runs with dependency-aware parallel execution.

Get a saved, cited report from your AI agent

Unreal Engine plugin for the DCC Model Context Protocol (MCP) ecosystem

An offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.

Minimal CLI agent framework with compounding project memory — gets smarter with every session. Clean, modular, any LLM provider

Rust library wrapping 12 AI CLI tools as pluggable LLM providers — with OpenAI API client, ACP headless mode, agent loop, MCP server, and OpenAI-compatible REST API

Multi-engine LLM benchmark & monitoring CLI for Apple Silicon

TypeScript AI agent framework where personality is architecture. Specialists, not chatbots.

No repository description published.

fold: the enterprise MCP gateway — one governed endpoint between every MCP client and every MCP server. Federation, auth, policy, rate limiting, caching, audit.

A local-inference-Llm-first coding agent with optional cloud inference from siGit Code Cloud or any OpenAI API compatible service.

Helen Agent Develop Language

Go AI Agent 框架，提供工具调用、图编排、多 Agent 协作、RAG 与持久化执行，支持 MCP、A2A 和 OpenTelemetry。

Embeddable agent kernel for durable, provider-neutral LLM agents with permissions, pluggable tools, observability, and subagents.

The server-side runtime for AI agents. Durable & crash-safe (event-sourced), multi-worker scheduling, per-session sandboxing, human-in-the-loop, provider-neutral. Host agents like Claude Code on your own infra — self-hostable, no vendor lock-in.

Relay any model into any coding agent

No repository description published.

Quickly reads webpages and converts to markdown for fast, token efficient web scraping

Quickly screenshots webpages and converts to an LLM friendly size

Validate and retry LLM outputs for ruby_llm. Describe the JSON response you expect, fall back to a stronger model when the cheaper one fails the rules, and gate CI on regressions — all as one contract object per step.

Your agent and your teammates' agents, comparing notes before the meeting would have happened. ettle reconciles each person's typed working state into coordination tangles — collisions, duplicated work, stale assumptions — and shows each human only what is theirs to act on. Local-first, privacy-bounded. Early Go PoC.

An open-source, provider-agnostic execution and replay infrastructure for AI applications, LLM applications, agents, agentic workflows, RAG systems, tool-using systems, and multi-agent systems.

Monorepo for the Krova Cloud JS/TS packages — SDK, CLI, MCP, webhook verifier, n8n node.

A lightweight, high-performance personal AI agent. Fast async core, pluggable tools, and open integration with external agent ecosystems (Claude Code, Codex, MCP). Simple to configure, easy to extend.

The production HTTP control plane for durable AI runs. Start, schedule, observe, and replay AI workflows across any client — terminal, browser, tray, Telegram, or email. Replay-first architecture with append-only ledger.

Unofficial .NET SDK for Langfuse