#llm

Official Python SDK + CLI for the Lenz fact-checking API — extract claims from AI output, assess or verify them, and get sourced verdicts with citations.

Anthropic Claude API wrapper for Go

The .NET library to build AI agents with 30+ built-in connectors.

Self-hosted Bun/TypeScript agent runtime with composable tools, memory, skills, transports, and policy.

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

🛀 Soothe - An autonomous expert system engineered to orchestrate complex workflows and execute long-duration tasks with precision and persistence.

AI agent debugging, collaboration, and trace observability. Built for teams using CrewAI, OpenAI, and more.

🏀 API FFBB — Modern async & typed Python SDK for FFBB public data (clubs, competitions, standings, lives) and Meilisearch search. Modern alternative to ffbb-api-client.

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-hosted redacting gateway.

🌍 Terraform Model Context Protocol (MCP) Tool - An experimental CLI tool that enables AI assistants to manage and operate Terraform environments. Supports reading Terraform configurations, analyzing plans, applying configurations, and managing state with Claude Desktop integration. ⚡️

Vendor-neutral Go CLI for the Open Knowledge Format. Create, validate, lint, index, search, and graph OKF bundles. Built to be driven by AI agents.

An open-source build system that compiles your specs and architecture into working code.

Make forms easier, LLM tools safer. Natural-language quantities, units, dates & ranges parsed into canonical values — zero dependencies, two-way.

Convert PDF documents to Markdown using Vision Language Models — CLI and library

Financial reconciliation for humans and AI agents like Claude, Codex, and others. Open source and deterministic.

The developper starter pack for document processing

Python CLI framework for tools AI agents can call safely: one-call manifest, JSON envelope on every exit, typed exit codes. Implements the CLI Agent Spec

Distribute AI Skills as Composer dependencies

Moonshot kimi k3 terminal based coding agent & harness running on your own Cloudflare account.

splyntra

Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,583 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.

🐍 Community-driven Python implementation of TOON

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

Ai training toolkit

TypeScript and Python toolkits and project scaffolding for building Unified Namespace applications.

MCP-Bastion: The Zero-Infrastructure Runtime Middleware ,Enterprise-Grade Security Middleware for the Model Context Protocol (MCP)

MCP server wrapping the MetaTrader 5 Python library, read market data, watch your trades, and place trades from your AI agent, with a consent/audit policy layer.

MCP server for Jira & Confluence — 22 tools, 15 resources, 5 prompts for custom fields, issue links, attachments, agile boards, sprints, versions, team calendars and sprint capacity. MCP 2026-07-28 (MCP 2.0); complements mcp-atlassian.

Stop repeating yourself to Claude.

llama_cpp.rb provides Ruby bindings for llama.cpp