HYSEN LABS DIRECTORY

#AI Agents

Capability tag · curated repositories and deep analysis.

4,568 curated open-source projects
Lyellr88

marm-memory

★ 418

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.

Python90 forks
burugo

one-mcp

★ 417

A centralized reverse-proxy platform for MCP servers — manage, group, and export as Skills from a single endpoint.

Go46 forks
★ 417

Simple CLI tool for deterministic routing of queries between local and hosted LLM models

Rust24 forks
freestylefly

wesight-obsidian

★ 417

WeSight Obsidian plugin for local agent runtimes.

TypeScript74 forks
adongwanai

learn-workbuddy

★ 417

Rebuild a WorkBuddy-style desktop AI assistant harness from scratch: a 24-chapter Python tutorial covering the agent loop, tool calling, memory systems, sidecar processes, sandbox auditing, and DeepSeek/OpenAI evaluation traces.

Python70 forks
GizClaw

flowcraft

★ 416

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

Go11 forks

Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing, and more

Python67 forks
★ 416

The semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, and connect telemetry, services, and business objects in one object graph.

Go65 forks
★ 416

Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback.

Python49 forks
Chenruishuo

posterly

★ 416

Build academic conference posters as a single HTML/CSS file, rendered to print-ready PDF via headless Chromium. A coding-agent skill.

Python10 forks
zeraix

zeraix

★ 415

Open-source local AI workspace — advancing on-device inference.

TypeScript13 forks
fcakyon

phd-skills

★ 415

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

Shell36 forks
Kocoro-lab

Kocoro

★ 414

A Mac-native AI agent with memory, local computer access, browser control, IM channels, and MCP-native integrations. Built on Shannon.

Go133 forks
KitionAI

kition

★ 414

Kition brings Markdown, DataTable, WhiteBoard, a tool-using AI agent, browser research, and visual workflows into one desktop workspace.

TypeScript31 forks
★ 413

Portable agent skill for research-style editable draw.io diagrams and screenshot-driven refinement

Python13 forks
treygrainger

ai-powered-search

★ 413

The codebase for the book "AI-Powered Search" (Manning Publications, 2025) and associated "AI-Powered Search: Modern Retrieval for Humans & Agents" Maven course

Jupyter Notebook122 forks
bassimeledath

dispatch

★ 413

A Claude Code skill that 10x's your effective context window by dispatching tasks to background AI workers.

Unknown20 forks
hardhackerlabs

podwise-cli

★ 413

CLI client for podwise.ai — turn any podcast episode into AI-powered insights, designed for use in AI agents and skills workflows.

Go17 forks
★ 413

Agent-friendly ComfyUI workflow skills for OpenClaw, Hermes Agent, Codex, and Claude Code; complementary to Comfy official local MCP.

Python40 forks
TheDesignFounder

DreamLayer-Eval

★ 413

DreamLayer Eval: open-source benchmarking for image and video diffusion models. Automate prompts, seeds, and metrics for reproducible results. A research project from DreamLayer AI (dreamlayer.io).

Python204 forks