# agent2

> The production runtime for AI agents. Schema in, API out. Built on PydanticAI + FastAPI.

- **URL**: https://www.freshcrate.ai/projects/agent2
- **Author**: duozokker
- **Category**: MCP Servers
- **Latest version**: `v0.4.0` (2026-04-30)
- **License**: MIT
- **Source**: https://github.com/duozokker/agent2
- **Homepage**: https://getagent2.dev
- **Language**: Python
- **GitHub**: 26 stars
- **Registry**: github
- **Tags**: `agent-runtime`, `ai-agents`, `ai-framework`, `developer-tools`, `docker`, `enterprise-ai`, `fastapi`, `llm`, `python`

## Description

The production runtime for AI agents. Schema in, API out. Built on PydanticAI + FastAPI.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v0.4.0` | 2026-04-30 | High | ## Agent2 v0.4.0 — Brain Clone Pipeline Upgrade  Single source of truth, operational learnings, and repo hygiene.  ### Added - **Operational learnings system** (`shared/learnings.py`): auto-logs low-confidence results, clarification patterns, and rejections after each agent run. The 3 most recent learnings are injected into the next run's prompt context. - **`/agent-qa` skill** for end-to-end testing of deployed agents with schema validation and health reporting - **Skill routing rules** in CLAU |
| `v0.2.0` | 2026-04-27 | High | ## Highlights - Adds the full Brain Clone flagship agent: procurement-compliance-officer. - Adds public market and interview example agents. - Updates Brain Clone skills around the Sachbearbeiter Chain-of-Thought pattern. - Adds Agent2 onboarding docs for AI coding agents via AGENTS.md, CLAUDE.md, llms.txt, and llms-full.txt. - Adds per-run _toolsets support from before_run() in the API runtime. - Adds procurement knowledge books and Promptfoo evals.  ## Validation - GitHub CI on main passed: Py |
| `v0.1.0` | 2026-04-02 | Medium | # Agent2 v0.1.0  **The production runtime for AI agents. Schema in, API out.**  ## What's included  - `create_agent()` + `create_app()` — two calls to go from schema to production API - Typed outputs via Pydantic `output_type` with automatic retries - Sync and async task execution - Pause/resume with serialized message history - Human-in-the-loop approval workflows - Provider routing for prompt cache optimization - Tool interception and collection scoping - Knowledge search via R2R + FastMCP - M |

## Dependency audit

- **Score**: 83/100
- **Total deps**: 9
- **Resolved**: 3
- **Unresolved**: 6
- **License conflicts**: 0
- **Warnings**: 2
- **Scanned**: 2026-05-11

## Citation

- HTML: https://www.freshcrate.ai/projects/agent2
- Markdown: https://www.freshcrate.ai/projects/agent2.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/agent2/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._