llm — independent software & tools
-
node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
-
nothumanallowed
Local AI assistant: 80 tools (Gmail, Calendar, Drive, GitHub, Slack, browser, code, files), 38 agents, visual workflows (Studio, AWF, WebCraft). Install with `npm i -g nothumanallowed`, run with `nha ui`. Free tier built-in (Liara), no API key required. Y
-
notion-axi
AXI-compliant Notion CLI for agents — token-efficient TOON output, contextual suggestions, idempotent mutations
-
obsidian-mcp-pro
The most feature-complete MCP server for Obsidian vaults — search, read, write, tag, link analysis, graph traversal, canvas support, and more.
-
ollama-ai-provider-v2
Use Ollama with the Vercel AI SDK, implementing the official Ollama API. This provider has minimal dependencies and is web-compatible out of the box.
-
omnius
AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop
-
openapi-mcp-generator
Generates MCP server code from OpenAPI specifications
-
@opentelemetry/instrumentation-openai
OpenTelemetry instrumentation for the `openai` OpenAI client library
-
@openuidev/react-headless
Headless React primitives for AI chat — state management, streaming adapters for OpenAI and AG-UI, message format converters, and thread management for OpenUI generative UI apps
-
pi-mcp-adapter
MCP (Model Context Protocol) adapter extension for Pi coding agent
-
pi-simplify
A Pi extension that reviews recently changed code for clarity, consistency, and maintainability.
-
@posthog/ai
PostHog Node.js AI integrations
-
@posthog/mcp
PostHog SDK for Model Context Protocol (MCP) servers — tracks tool usage, intent, and identity
-
prjct-cli
Project memory and workflow context for AI coding agents.
-
@retineo/core
Connection discovery engine (L0–L3). Open-source core for the Retineo ecosystem.
-
@ruvector/ruvllm
Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference
-
sanook-cli
A terminal AI coding agent — BYOK, 9 providers, MCP, cron gateway, skills, and git awareness. Built from scratch in TypeScript.
-
seekstone
Obsidian MCP server for Claude — filesystem-direct vault access, 575× smaller payloads than the REST plugin.
-
slopcode
The open source AI slopcoding agent.
-
specrails-core
AI agent workflow system for Claude Code — installs 12 specialized agents, orchestration commands, and persona-driven product discovery into any repository
-
stably
AI-powered E2E Playwright testing CLI. Stably can understand your codebase, edit/run tests, and handle complex test scenarios for you.
-
@structured-world/gitlab-mcp
Advanced GitLab MCP server
-
@swarmvaultai/engine
Core engine for SwarmVault: ingest, compile, query, lint, and provider abstractions.
-
@tanstack/ai
Type-safe TypeScript AI SDK for streaming chat, tool calling, agents, structured outputs, and multimodal generation.
-
tokenjuice
Lean output compaction for terminal-heavy agent workflows.
-
@toon-format/toon
Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware encoding of JSON for LLM prompts
-
@trenchwork/coder
Claude Code–class Ink TUI agent for DeepSeek v4 Pro (max thought, ultracode always on). Live follow-up queue, Shift+Tab permission modes, colored diffs, adversarial verifier — your keys, no login. Independent; inspired by Project Glasswing.
-
veryfront
The simplest way to build AI-powered apps
-
claude-memory
Enable persistent memory for Claude that works across crashes and restarts in both Claude Code and Claude Cowork environments.
-
sublarr
Self-hosted subtitle manager & LLM translator for anime and media — *arr-compatible, fully local
-
AgentMind
Enhance AI agents with metacognition and persistent memory to improve thinking processes and retain context across sessions.
-
ai-tools
🧠 Discover versatile AI tools for seamless chat experiences, enabling multi-model support and enhanced productivity across platforms like Windows and Mac.
-
mcp-yandex-tracker
Manage and automate tasks in Yandex Tracker using a robust MCP integration for efficient issue tracking and project control.
-
botference
One room, three minds: a multi-LLM planning council for your terminal — you, Claude Code, and Codex debate and ship an implementation plan.
-
opti-oignon
Local-first AI inference platform for LLMs — private chat, RAG, defense-in-depth security (Daily/Bulbe, encryption at rest, 2FA), on your own hardware. SvelteKit + FastAPI
-
SmartRAG
📄 Enable smart conversations with documents, images, and audio files using this advanced Retrieval-Augmented Generation system.
-
AgentGuard
Protect AI agents by detecting and blocking prompt, command injection, Unicode bypass, and social engineering attacks with customizable security controls.
-
dumpall
📦 Aggregate and format file contents into clean, LLM-friendly Markdown for easy sharing, code reviews, or archiving with this versatile CLI utility.
-
Pokemon-Claw-Monitor
Provide real-time monitoring with a Pokemon-themed dashboard that visualizes OpenClaw agents in a customizable pixel-art office space.
-
SelfAgent
🤖 Build a self-hosted AI assistant to manage files, browse web, write code, and chat via a WhatsApp-style interface using your own API keys.
-
Bamboo-agent
Bamboo — a local-first AI agent runtime in Rust: tasks, tools, memory, MCP, workflows and schedules behind an HTTP + SSE API. The self-contained execution core powering the Bodhi desktop agent.
-
commune-cookbook
Provide AI agents with real email and phone identities using production-ready tools compatible with LangChain, CrewAI, and other frameworks.
-
svar
Type‑safe LLM output for Clojure. Works with any text‑only model.
-
ivygrep
Semantic Grep - Superpower Your LLM
-
longhouse
Self-hosted mission control for CLI coding agents — one searchable timeline for Claude Code, Codex & more, across your machines, with live remote control.
-
acolyte
A terminal-first AI coding agent. Open-source, observable, and built for developer control.
-
llmXive
llmXive is an LLM-driven system for automating scientific discovery
-
mcp-superset
Extend Apache Superset with Model Context Protocol to integrate and manage machine learning models efficiently within data dashboards.
-
claude-compaction-viewer
View and analyze Claude Code conversation history and compaction events with a TUI and CLI tool for clear session insights.
-
PRISM
AI-Native Autonomous Materials Discovery Platform
-
openclaw-memory-kit
Provide AI agents on OpenClaw with a full memory system for context saving, auto backups, file management, and session recovery.
-
jarvis
Autonomous AI Desktop Agent for Linux – Multi-LLM, Desktop Control via VNC, WhatsApp Integration, RAG Knowledge Base, OpenClaw Skill Ecosystem
-
claude2api-deploy
Deploy a proxy that converts Claude.ai sessions into a standard Anthropic API with streaming, tools, and image support.
-
drt
Reverse ETL for the code-first data stack
-
claude-terminal
Manage multiple Claude Code sessions in a single terminal with tabs, session persistence, multi-project workspaces, and git worktree support.
-
jobclaw
Streamline hiring by connecting AI agents that evaluate, negotiate, and schedule interviews to reduce time and improve candidate fit.
-
daydream
Agentic code-review CLI that records each review/fix/test run trajectory, building a corpus for fine-tuning open-weight models.
-
claude-pi
Delegate deterministic coding tasks from Claude Code to Pi for efficient parallel processing, looping, and pipeline management in AI workflows
-
asya-chat-ui
Build multi-organization LLM chat platforms with model routing, tool execution, usage analytics, and OpenAI-compatible APIs.
-
Claude-Code-Agent-Monitor
Monitor and visualize Claude Code agent sessions, tool use, and orchestration in real-time with a Node.js and React dashboard integrated via native hooks.