HYSEN LABS DIRECTORY

#AI Agents

Capability tag · curated repositories and deep analysis.

4,545 curated open-source projects
★ 474

Talk to Fengge: clone anyone's voice and personality for real-time conversation, with under 1 second of engineering latency.

Python95 forks
GamePhanesStudio

GamePhanes

★ 474

An open-source game coding agent environment and benchmark for Godot.

Python7 forks
Kulaxyz

token-diet

★ 473

Always-on token-efficiency skill for coding agents (Claude Code, Codex, Cursor, Windsurf, Cline). ~31% lower bill on average, no loss of correctness.

Shell4 forks
★ 473

A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page, designed for LLM RAG

Python53 forks
MiniCodeMonkey

chief

★ 473

Build big projects with Claude. Chief breaks your work into tasks and runs Claude Code in a loop until they're done.

Go51 forks
★ 472

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

Python66 forks
builderz-labs

marketing-dashboard

★ 472

Local-first marketing operations control center for CRM, outreach, content, analytics, approvals, automations, and agent workflows.

TypeScript23 forks
juyterman1000

entroly

★ 472

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

Python71 forks
heygen-com

skills

★ 472

HeyGen AI agent skills — avatar creation and video production via the v3 Video Agent pipeline

Shell79 forks
morapelker

hive

★ 471

Project/Worktree manager, deeply integrated with AI agents to increase productivity and multitask efficiently

TypeScript55 forks
ratel-ai

ratel

★ 471

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

TypeScript26 forks
AgentSkillOS

SkillAnything

★ 471

Making ANY Software Skill-Native -- Auto-generate production-ready AI Agent Skills for Claude Code, OpenClaw, Codex, and more.

Python49 forks
beilusaiying

always-accompany

★ 471

Companionship, chat, coding and work share one memory and context framework, the kind of AI from science fiction that keeps you company and gets things done with you. A diversified agent project built on context and attention mechanisms.

JavaScript6 forks
jayminwest

warren

★ 471

Run coding agents like infrastructure, not terminal sessions. Warren manages isolation, lifecycle, spend, recovery, and Git delivery on compute you control.

TypeScript93 forks
RickyTong1

audit-harness

★ 470

Three-layer audit enforcement framework for AI agents — hooks, skills, context recovery, and audit-driven daily reports

Shell3 forks
eigenpal

docx-editor

★ 470

Open-source WYSIWYG .docx editor library for React and Vue with canonical OOXML, tracked changes, and real-time collaboration. Agent-ready.

TypeScript98 forks
nicksp

dotfiles

★ 470

My personal dotfiles: Zsh, Git, VSCode, Obsidian, Ghostty, cmux, etc.

Shell101 forks
★ 470

OKX trading MCP server — connect AI agents to spot, swap, futures, options & grid bots via the Model Context Protocol.

TypeScript76 forks
★ 470

Living project docs for coding agents: keep guides, progress logs, change maps, and handoff context updated as your repo evolves.

Python7 forks
hopechen067

MapStage

★ 470

MapStage live tuner: map/globe, satellite, hypsometric relief, region isolate, Mapterhorn DEM, JSON presets.

JavaScript63 forks