#llm

A kinda close-enough xml for LLM

A TypeScript library for validating and securing LLM prompts — PII, jailbreak, prompt injection, profanity, toxicity and relevance guards. Zero-config defaults, extensible with custom patterns.

🔁 Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM — discover → implement → verify → merge → 24/7 — behind safety gates, at up to 90% fewer tokens. 48 extension points. Not a chatbot. A worker.

AI security gateway that inspects every prompt and response through a multi-layer detection pipeline - enforcing ALLOW, BLOCK, or SANITIZE before anything reaches the model.

Proof-first software factory for AI-assisted code: specs, adversarial gates, deterministic decisions, and reviewable receipts.

Verifiable coding-agent harness in Go: external test gates, typed outcomes, sandboxed execution, multi-model providers, and signed proof bundles.

Terminal LeetCode coach — hints, not answers. Spaced review + ACM mode.

Connect agents across runtimes, frameworks, and teams.

SigRank MCP — the yield cascade + live leaderboard as MCP tools any agent can call. On-device token scanner + tabbed TUI dashboard. npm i -g sigrank

Jurisdiction-aware judicial reasoning platform — a model-agnostic AI engine that produces citation-backed, adversarially-tested draft case analyses for human sign-off. Non-binding by design.

Command-line interface for the Adapto CMS management API. Give LLM agents full knowledge of the CLI (for MCP/tool-use scenarios).

JavaScript/TypeScript SDK for AI2Web: build the /ai2w manifest, serve the routes, and project to MCP, ACP, AP2, GraphQL & OpenAPI for AI agents.

MCP server with 30 tools for block chain data and ops— setup, token lookups, wallet balances, live chain queries using micro payment on x402.

用最少的代码复刻 OpenClaw 的 agent 运行原理

High-Precision GraphRAG. Native to PostgreSQL.

Strip AI tells from text: em-dashes, slop words, and stock phrases, in one deterministic local pass. CLI, GitHub Action, Obsidian plugin, and MCP server.

Fast and powerful templates. Valid markdown. Strongly typed and great for agents. Supports Rust, Python, Go, TypeScript

Multiplexer for LLMs - route prompts to multiple backends and orchestrate multi-step workflows

Validate API keys for OpenAI, Anthropic, Google Gemini, Groq, Mistral, OpenRouter, Cohere, DeepSeek, Together, Fireworks, xAI, and Perplexity. Zero dependencies. CLI + library.

A read-only, lightweight, and integratable AI code review CLI open-sourced by Zadig. Supports local and CI scenarios, multiple LLM backends, and extensible rule engine.

AI Agent SDK designed for Go developers

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.

Loom is a high-performance, graph-based AI workflow engine for Go. It allows you to build complex agentic systems by defining multi-step workflows as directed graphs, seamlessly connecting them to any large language model, and persisting execution state for long-running or interrupted tasks.

Hey LLM, you okay? — pyramid-ordered LLM testing CLI for CI/CD. One YAML for every layer, LLM-as-a-judge gates, and A/B triage that tells prompt regressions from model drift.

Research Vault — an AI research-assistant framework

AI SDK provider for Mixlayer — the fully oxidized inference API

A SQLite mailbox for local LLM agents — one HTTP API, an ActivityStreams messaging model, and a local stdio MCP server so AI coding agents can message each other. No external services.

Tako CLI — AI coding tools launcher

A high-performance, enterprise-grade large model gateway dedicated console designed for the power ecology of large models (LLM) with rich traffic governance strategies.

LLM facade for the Stapel framework: provider-swappable completions & translation, prompt ledger with token accounting