Give agents durable memory, searchable decisions, and synchronized working documents while keeping knowledge sovereignty at the center.
openclaw plugins install @brainfork/brainfork-openclawOpenClaw Quickstart
Generate a Brainfork token, drop in your endpoint, and let the plugin recall and sync memory automatically.
plugins:
slots:
memory: brainfork-openclaw
entries:
brainfork-openclaw:
config:
baseUrl: https://api.brainfork.is
endpoint: your-server-endpoint
apiKey: bf_live_...
autoRecall: true
autoIndex: true
captureDecisions: trueBrainfork stores documents, decisions, and retrieval context in a hosted memory layer that stays portable and inspectable. OpenClaw gets a first-class memory plugin. You keep the source of truth.
That means fewer ad hoc prompts, less local-file drift, and a cleaner path to future graph-based retrieval without forcing the agent runtime to change again.
Inject relevant Brainfork context before the agent starts, without dumping your whole archive into the prompt.
Push `MEMORY.md` and `memory/**/*.md` into Brainfork with deterministic hashes, updates, and cleanup.
Your knowledge stays in a Brainfork server you control, with decisions and documents preserved beyond any single model vendor.
Install the plugin, point it at your Brainfork server, and let it push documents, log decisions, and recall the right context before each run.
1
Create a Brainfork server and token.
2
Install the plugin and set the memory slot.
3
Let OpenClaw sync `MEMORY.md`, recall context, and keep decisions durable.
Pricing
Includes 25k requests and 1k indexed documents each month. Overage is €1 per 10k extra requests and €1 per 250 extra indexed documents.