Agent-Me v2.0.0 — Auditable multi-agent RAG reference implementation

Agent-Me v2.0.0 provides a runnable open-source reference implementation for inspecting grounded, role-based multi-agent workflows, paired with a bilingual hands-on engineering curriculum.

Reference implementation highlights

• Planner → Researcher → Critic → Writer orchestration with immutable typed handoffs
• Deterministic retrieval over a reviewable Markdown knowledge base
• Evidence-aware answers, critic-gated abstention, and safe operational traces
• Repeatable behavioral evaluation for supported and unsupported requests
• FastAPI + React reference stack with contract tests and Docker Compose integration in CI
• Local extractive and collaboration paths that do not require a paid model API

The agents are sequential, in-process role stages. This release does not claim a distributed runtime, autonomous swarm, general-purpose agent SDK, factual-correctness guarantee, or production-ready enterprise platform.

Engineering curriculum

The eight numbered lessons explain and rebuild the same architecture used by the reference implementation. Complete learning paths are available in English and Simplified Chinese, with a rubric, glossary, contribution workflow, and reproducible labs.

Start here

1. Run the reference implementation.
2. Inspect the architecture.
3. Follow the engineering learning path.
4. Ask questions in Discussions Q&A.

Upgrade note

This release moves beyond the original starter demo by combining a tested reference implementation with a structured bilingual curriculum. Existing API routes remain available.

Full changes: v1.1.0...v2.0.0

Agent-Me v1.1.0

Highlights

• Professional, project-style canonical README
• Eight translated project overviews plus English
• Nine-language web interface
• Browser locale detection and persisted manual language selection
• Typed translation completeness guarantees
• Localization contribution guide and expanded tests

See pull request #7 for implementation and verification details.

Agent-Me Starter v1.0.1

Improves local container builds by excluding frontend dependency and build-output directories from the Docker context.

Agent-Me Starter v1.0.0

First clean public release of the grounded personal Q&A agent framework. Includes FastAPI, React, local extractive retrieval, optional OpenAI-compatible inference, containers, tests, CI, and security guidance.