#5656th of 70 in Agent frameworks and SDKs
agent-native
TypeScript framework for agents that share actions and state with an app UI
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 7.1k
- License
- no license
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
Missed the latest GitHub check; these facts may be older.
Overview
Agent-Native is a TypeScript framework where each capability is defined once as a zod-validated action. The agent calls it as a tool, and the React UI calls it through hooks such as useActionQuery. The same action is also exposed over HTTP, MCP, A2A and CLI. It ships agent chat, auth and permissions, skills and memory, scheduled automations, and PostgreSQL storage (PGlite for local development).
Who it is for: TypeScript developers building agent apps with a custom UI
Strengths
- One action definition serves agent tool, UI call, HTTP, MCP, A2A and CLI
- Agent and UI share validation, permissions, data and current UI state
- Includes auth, memory, automations and agent teams out of the box
- Sample apps (Mail, Calendar, Slides, Analytics and others) to fork as starting points
Weaknesses
- README does not list supported LLM providers or models
- Examples and hooks are React-oriented; other front-ends are not documented in the README
- No Docker or compose setup shown in the README
- Production database is PostgreSQL only, per the README
What it needs
- Needs Node.js, PostgreSQL (production), PGlite (local development), LLM provider
Also in Agent frameworks and SDKs
See all 70| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 94 out of 100 |
| 2 | langchainPython framework for building LLM agents and apps from interoperable components | 89 out of 100 |
| 3 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| #4 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 89 out of 100 |
| #5 | mastraTypeScript framework for building AI agents and workflows | 89 out of 100 |