Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
- golang
- observability
- opentelemetry
- policy-engine
47,133 repositories indexed
769–792 of 837 · Most stars
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory, RAG and observability. Plug-and-play from chat UI to full agents.
Reverse ETL for the code-first data stack
You need customized prompts for your tasks! 🤏SimpleGPT is a Vim plugin designed to provide a simple yet flexible way to customize your prompts for your tasks or building chat on nearly all kinds of LLM APIs.
Self-hosted AI-assisted CTI-to-detection workbench for ATT&CK mapping, IOC/CVE intelligence, Threat Radar, malware triage, Attack Simulation, and SIEM validation.
A Common Lisp LLM completions library
Generalized Diffie-Hellman key exchange Java library built on top of the Vert.x framework
The Karpathy LLM Wiki pattern, productionized. MCP server that gives Claude a librarian for your Obsidian vault — graph traversal, auto-wikilinks, trigram search.
Sonntagsfrage is an iOS 14 Widget displaying current polls for upcoming elections in Germany.
Spends CPU cycles so you don't spend tokens. The LLM gets a briefing packet instead of a flashlight in a dark room.
use Local LLM on PowerToys Run
Enterprise-grade platform to generate and execute Cypress, Playwright, WebdriverIO, and Appium end-to-end tests from natural language requirements. (Appium is experimental and requires external mobile infrastructure.)
Minimal JS implementation of older cryptography algorithms: RSA, DSA, DH.
The tested, tool-agnostic AGENTS.md kit — verified templates, a CI linter, and migrators from .cursorrules/CLAUDE.md/Copilot/Windsurf/Cline/Aider.
Lightweight AI agent runtime for Go. Define multi-agent crews in YAML, run them with goroutines and channels, and let the runtime handle scheduling, parallelism, retries, and observability — without leaving the Go ecosystem.
A Neovim plugin that uses LLMs to improve the grammar and spelling of natural language text.
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
Transform Git history: rewrite, clean, and optimize your repositories with ease.
A Common Lisp LLM chat library
Trust metadata for AI agents — a stamp costs ~15 tokens, re-verifying costs 15,000. Agents stamp what they verify; the next agent runs 'akf check' and builds on it. pip install akf
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Claude Code / Codex / Gemini. Eval-gated 100/100, you always merge.
Memory management and retrieval for Claude Code
Haskell library implementing OpenFlow protocol versions 1.0 and 1.3