New: Decision Runtime — closed-set judgments for Agent OS. Read the guide →
HazelJSStarter
Research Agent
Collect sources, build knowledge, synthesize findings, and maintain durable research context.
What to build
A research agent with retrieval, memory, and evaluable outputs.
Suggested architecture
- 1Research question↓
- 2Research Agent↓
- 3Collect sources (RAG)↓
- 4Synthesize↓
- 5Persist memory↓
- 6Report + eval hooks
Minimum acceptance criteria
- Public GitHub repository
- Uses @hazeljs/agent
- RAG or retrieval integration
- README with setup instructions
- Durable research context across turns
Optional advanced goals
RAGMemoryEvalObservability
Submit Research Agent
This form saves your project to our database. We review it for the community showcase — you do not open a pull request.
Submit your repository
Public GitHub repos only. This form saves your project to our database. We review it before it can appear on the community showcase — you do not open a pull request.