#llm

Z.AI API client SDK for Go - Comprehensive OpenAI and Anthropic API integration

Ask your repo what breaks before an AI coding agent edits it.

A tool for detecting architectural drift with LLMs

agentgg cli

AI-first server monitoring via MCP — Docker, systemd, remote hosts

Sandhi — the metering layer for AI agents. An open-source AI usage gateway: meter, attribute, and budget every model call across shared keys.

AiO webtools for Pi: Search, Fetch, Pull

Multi-agent orchestration harness for Claude Code + Codex — task lifecycle, handoff protocol, dashboard, and autonomous dispatch

GRASP — Code architecture visualizer + 150-tool MCP server. Dependency graphs, security scanning, multimodal knowledge graph, ORM tracking, git change impact, graph schema v3. Works with GitHub, GitLab & local dirs. 35 languages. Zero data collection.

No repository description published.

TypeScript SDK for orchestrating Agentic Systems — concurrency, structured output, cost control, and consensus as first-class primitives.

Open-source governance control plane for coding agents — per-run identity, brokered credentials, layered egress, approvals, and an append-only audit. Apache-2.0, self-hosted.

No repository description published.

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

Keep Claude Code and Codex aligned with task requirements through intent proof, drift checks, visible run state, and evidence-based verification.

Nx + pnpm monorepo for RhombusKit — a framework-agnostic design token system and Angular component library. Ships @rhombuskit/tokens, @rhombuskit/theme-engine, @rhombuskit/material-preset, and @rhombuskit/core.

Multi-engine LLM benchmark & monitoring CLI for Apple Silicon

A single interface in Go to get inference from multiple llm/ai providers using their official SDKs

Provider-agnostic multi-LLM abstraction for the Greentic platform

Unified batch API for AI providers. Save up to 50% on LLM costs.

Training-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated.

Autonomous AI agents you deploy in 30 seconds across any channel. Zero-config CLI, 37 channel adapters, HEXACO personality and cognitive memory powered by AgentOS, five-tier prompt-injection defense.

ClinePass provider for pi — 11 curated open-weight coding models (GLM-5.2, Kimi K2.7 Code, Kimi K3, DeepSeek V4, Qwen3.7, and more)

Beautiful git diff viewer, generate commits with AI, get summary of changes, all from the CLI

Local mock server for web services, including Google Workspace, GitHub, and more! No authentication required.

Security boundary CLI proxy between AI coding agents and your shell — redacts secrets, neutralizes prompt injection, wraps untrusted terminal output, and audits every command. Single Rust binary.

No repository description published.

Python SDK for m8tes — give every customer their own AI agent through one API. Hosted runtime, 150+ integrations, scheduling, memory, human-in-the-loop.

An AI-driven dynamic protocol fuzzer for the Model Context Protocol (MCP). Prove runtime exploitability by discovering state violations, transport crashes, and application-layer logic flaws (SSRF, LFI) before your AI agents do.

"Unit tests" for your agent skills