# Recipes

https://github.com/user-attachments/assets/9454662f-2648-4928-8723-f7d52e94e9b8

Step-by-step builds that add a new capability to your Open Brain. Follow the instructions, run the code, get a new feature. Some recipes depend on canonical skill packs in [`skills/`](../skills/); those recipes should install the skill first, then use the recipe for workflow and composition.

| Recipe | What It Does |
| ------ | ------------ |
| [Bring Your Own Context](bring-your-own-context/) | Portable context workflow that packages extraction prompts, profile generation, and remote MCP deployment into one entrypoint |
| [Email History Import](email-history-import/) | Pull your Gmail archive into searchable thoughts |
| [ChatGPT Conversation Import](chatgpt-conversation-import/) | Ingest your ChatGPT data export |
| [Daily Digest](daily-digest/) | Automated summary of recent thoughts via email or Slack |
| [Wiki Compiler](wiki-compiler/) | Compiles graph-backed entity pages and topic synthesis into a regenerable wiki layer you can run on demand or on a schedule |
| [Work Operating Model Activation](work-operating-model-activation/) | Interview-driven workflow that stores how you actually work and generates agent-ready operating files |
| [World Model Diagnostic Activation](world-model-diagnostic-activation/) | Lightweight activation path for a 20-minute world-model diagnostic that uses the base OB1 connector and a direct-paste fallback |
| [Research-to-Decision Workflow](research-to-decision-workflow/) | Compose canonical skills into operator and investor paths for analysis, synthesis, meetings, and decision documents |
| [NBJ OB1 Agent Memory for OpenClaw](openclaw-agent-memory/) | Canonical recipe for using OB1 Agent Memory as the governed continuity layer for OpenClaw workflows |
| [OpenClaw Code Review Memory](openclaw-code-review-memory/) | Flagship workflow for compounding repo-specific review lessons, maintainer corrections, and false positives |
| [OpenClaw TaskFlow Work Log](openclaw-taskflow-work-log/) | Durable handoff recipe for long-running OpenClaw TaskFlows across agents, models, and channels |

Agent Memory recipes should be paired with
[Safe Agent Memory and Provenance](../docs/safe-agent-memory-provenance.md)
before enabling write-back in shared workspaces.

## Contributing

Recipes are open for community contributions. See [CONTRIBUTING.md](../CONTRIBUTING.md) for details.