A Textual User Interface for interacting with Atlassian Jira from your shell

Finance terminal, in your terminal.

Bundled multi-agent orchestration harness for OpenCode. One install, complete control.

The most RAM efficient harness

An offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.

The open source coding agent.

Julia Language interface to RocksDB key-value store

Dynamic context pruning plugin for OpenCode - intelligently manages conversation context to optimize token usage

Psychology-grounded selective memory system for AI agents (Claude Code, OpenCode) with STM/LTM consolidation, decay curves, and learned importance weights

Julia bindings for tree-sitter.

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or…

Run OpenClaw, (formerly Moltbot, formerly Clawdbot) on Cloudflare Workers

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

Persistent memory for Claude Code — never lose context between sessions

Claude Code workflow for AI-mentored development. Work efficiently with Spec-Driven Development and the 6 Gates. Built to fight cognitive offloading — for developers using AI to grow and maintain o…

The open-source alternative to Claude Cowork (powered by opencode)

Functional and persistent data structures for Julia

sharing current agents in use

Multilingual Document Layout Parsing in a Single Vision-Language Model

Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

A graph DB-based MCP memory server for coding agents with intelligent relationship tracking

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

Beads - A memory upgrade for your coding agent

AirLLM 70B inference with single 4GB GPU

HY-Motion model for 3D human motion or 3D character animation generation.

Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.