llm

⛓️ build cognitive systems, pythonic

Demo of a customer service agent (Cymbal Air) using LangGraph, Tools, and RAG to interact with Google Cloud Databases via MCP Toolbox.

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimization of a goal.

Self-hosted, OpenAI-compatible AI gateway for private RAG, natural-language data access, and tool-calling agents.

Safely run OpenCode, Codex, Claude Code with full permissions.

🤖 Admyral enables continuous control monitoring for any custom control

My journey to learn and grow in the domain of Machine Learning and Artificial Intelligence by performing the #100DaysofMLCode Challenge. Now supported by bright developers adding their learnings :+1:

Open-source Tax Guides for AI agents, reviewed by named CPAs/CAs/EAs. 1,000+ Guides across 190+ jurisdictions. MCP server included. Works with Claude, ChatGPT, Cursor.

CTX: a tool that solves the context management gap when working with LLMs like ChatGPT or Claude. It helps developers organize and automatically collect information from their codebase into structured documents that can be easily shared with AI assistants.

Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Claude Agent SDK

Attribute (or cite) statements generated by LLMs back to in-context information.

⚡ Local chat assistants with AI superpowers

Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.

Super-Efficient RLHF Training of LLMs with Parameter Reallocation

SOTA Math Opensource LLM

(NeurIPS D&B 2024) STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).

Web UI & dashboard for Hermes Agent — chat, memory, skills, terminal, approvals, multi-agent orchestration. Self-hosted.

AI-powered legal compliance assistant for alcohol beverage pricing laws — extracts, analyzes, and explains New York state-level regulationsusing RAG + knowledge-graph reasoning.

Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.