#llm

A minimal, composable Go library for building AI agent applications.

Terminal coding agent with durable memory, hash-gated skill trust and a 61-task eval harness. Works with any OpenAI-compatible backend (GLM / DeepSeek / Qwen / Ollama).

Claude & Codex CLI but with safety 3rd and God Mode always.

the trust layer for agent memory

MCP server for Nano Banana AI image generation and editing via Ace Data Cloud.

MCP server for ByteDance Seedream image generation and editing via Ace Data Cloud.

Semantic memory for AI agents — local-first MCP server with hybrid search, governance, and consolidation

Expose djangorestframework-services services and selectors as a Pydantic-AI toolset.

Model Context Protocol server for DeepSeek's advanced language models

Companion intelligence for autonomous agents with real-time supervision, escalation, and human approval loops.

Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any GGUF on your exact hardware, self-calibrates, emits the exact llama.cpp command — or 'quantprobe auto' does it all. Falsification-tested laws; misses published at full size. pip install quantprobe

Retrieval and Retrieval-augmented LLMs

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Token-Oriented Object Notation - A compact data format for reducing token consumption when sending structured data to LLMs (PHP implementation)

Open-source AI security benchmarking CLI. Measure how AI models perform offensive security tasks with MITRE ATT&CK analysis and KSM scoring.

🩺 Doctor for your repo's AI harness — audit, merge & drift-guard scattered agent configs (AGENTS.md / CLAUDE.md / .cursorrules) into one source of truth. Real evals: 6/28 → 28/28 correct, −27% latency. Field-tested on react, vscode, n8n + 11 more. Claude Code · Codex · Cursor · Gemini

An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.

Lint the documentation & metadata quality of VGI (Vector Gateway Interface) data workers — descriptions, column comments, tags, and example queries — with a quality score, per-version baselines, and agent-friendly output.

Single-binary Go MCP server that wraps whatsmeow to expose a personal WhatsApp account as 42 MCP tools (messaging, groups, polls, media, privacy).

swarmdo — self-contained AI agent orchestration for Claude Code (swarmdo.com)

Multi-tier AI orchestration CLI — built for developers who think in systems.

Read-only-by-default MCP server for PostgreSQL. Query, introspect schemas, explain plans, health checks.

One zero-dependency CLI for all your MCP tools and agent skills. 99.2% fewer tokens on tool discovery, one config for every agent, nothing pre-installed. | 一个零依赖 CLI，管所有 MCP 工具和 Agent 技能。工具发现省 99.2% token，一份配置通吃所有 Agent，原生不预装。227KB，纯 Python 标准库。

Small polyglot cost ledger for LLM and agent API calls

Convention over configuration for agentic development teams

EDINET XBRL parsing library and MCP server for Japanese financial data

Shared infrastructure for go-* MCP servers: env, llm, cache, retry, metrics, strutil

MCP server for DeepSeek V4 (v4-flash, v4-pro, 1M context): chat, reasoning, function calling, thinking mode, cost tracking. deepseek-chat/reasoner aliases supported.

Most tools check the code your agent wrote. nullius checks how it got there — citations, session journals, weakened tests.

Vercel AI SDK community provider for OpenCode SDK - Use OpenCode configured providers via SDK