LIghtJUNction/humangrant

LIghtJUNction profile

Latest recorded source activity: October 11, 2026 at 21:34

SkillsMP catalog refreshed: October 17, 2026 at 00:09

skills collected: 2

GitHub stars: 1
GitHub forks: 0

Repository README

Repository README source: README.md

Read the source README

Expand full README

<img src="assets/wordmark.svg" alt="HumanGrant" width="100%"> An open protocol for AI agents to sign in with human permission. English · <a href="README.zh-CN.md">简体中文</a> <a href="https://github.com/LIghtJUNction/humangrant/actions/workflows/ci.yml"><img src="https://github.com/LIghtJUNction/humangrant/actions/workflows/ci.yml/badge.svg?branch=main" alt="CI" height="24"></a> <a href="spec/v0.1.md"><img src="assets/badges/protocol.svg" alt="Protocol 0.1" height="24"></a> <a href="Cargo.toml"><img src="assets/badges/rust.svg" alt="Built with Rust" height="24"></a> <a href="migrations/0001.sql"><img src="assets/badges/sqlite.svg" alt="SQLite" height="24"></a> <a href="openapi.yaml"><img src="assets/badges/openapi.svg" alt="OpenAPI 3.1" height="24"></a> <a href="skills/"><img src="assets/badges/skills.svg" alt="2 Agent Skills" height="24"></a> <a href="LICENSE"><img src="assets/badges/license.svg" alt="MIT License" height="24"></a> <a href="spec/v0.1.md">Protocol</a> · <a href="openapi.yaml">API</a> · <a href="examples/README.md">Examples</a> · <a href="docs/integration.md">Integration</a> ## Add to your project <a href="skills/humangrant-integrate/SKILL.md"> <picture> <source media="(prefers-color-scheme: dark)" srcset="assets/continue-with-human-beings-dark.svg"> <img src="assets/continue-with-human-beings.svg" alt="Continue with human beings" width="368" height="64"> </picture> </a>  ```text Read https://github.com/LIghtJUNction/humangrant/blob/main/skills/humangrant-integrate/SKILL.md and add HumanGrant to this project. ```  ## How it works **Request → Approve → Act** The agent sends you a link or email invitation. You open it on your device and choose the actions and resources it can use. Already signed in? Go straight to approval. The agent continues with its own identity. You can revoke access at any time. ## Run locally With Rust and Python installed: ```sh git clone https://github.com/LIghtJUNction/humangrant.git cd humangrant python -m venv .venv . .venv/bin/activate python -m pip install -r requirements-dev.txt python examples/setup_demo.py --dir .state cargo run -- serve .state/config.json ``` Open <http://127.0.0.1:8787>. Follow the [full example](examples/README.md) to connect an agent and read a note, or see [deployment](docs/deployment.md) for a remote server. ## Agent skills | Skill | Use it to | | --- | --- | | [humangrant-integrate](skills/humangrant-integrate/SKILL.md) | Add HumanGrant to an existing project. | | [humangrant-use](skills/humangrant-use/SKILL.md) | Request permission and continue a task. | Give your agent a skill link, or copy the skill's folder into your client's skill directory. --- [Contributing](CONTRIBUTING.md) · [MIT License](LICENSE)

Loading the repository README…

Skills in this repository

classification pending

skill

occupation

description

updated

humangrant-integrate

unclassified

Add HumanGrant account-to-agent authorization to an existing project. Use when the user asks for HumanGrant, Continue with human beings, or AI sign-in with human permission. Inspect real code, keep current human login, implement scoped AI sessions, and verify…

2026-10-11

humangrant-use

unclassified

Obtain and use limited HumanGrant permission as a running AI client. Use when a service offers Continue with human beings or a HumanGrant Markdown status page and a task needs account-authorized access. Keep the AI key local, request minimum scope, contact…

2026-10-11

Showing 2 of 2 collected skills.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/LIghtJUNction/humangrant.