Local evidence ledger for agent work

Short answer: use MiseLedger as the local evidence archive, and Brigade’s evidence station to install, plan crawls, and export verify/run receipts into it. Crawl and import stay operator-run at a process boundary; Brigade does not silently upload logs.

The problem

Agent work leaves scraps: session transcripts, verify receipts, git commits, chat exports. Grepping folders does not scale. Hosted “agent analytics” products require trust and network access you may not want for private work.

The path

brigade add evidence              # installs miseledger (Go binary)
brigade evidence crawl plan       # review-only init/crawl/doctor commands
# run the printed miseledger crawl commands yourself
brigade evidence export plan      # review-only receipts export path
brigade receipts export miseledger --target . --new-only --import
brigade evidence doctor

Pipeline in plain language: crawl local sources → adapter JSONL → MiseLedger SQLite + FTS → evidence briefs on the next Brigade run.

What stays a boundary

• MiseLedger stays a separate Go binary.
• Brigade plans and health-checks; it does not crawl sessions from brigade evidence commands alone.
• Receipt export is local and fail-open when the binary is missing.

When this is enough

Use MiseLedger + Brigade when you want local FTS over agent history and receipt-linked evidence on future runs. Use a hosted observability product when you need multi-tenant dashboards, SSO, or team-wide cloud retention policies.

Questions

Is this the same as memory handoffs? No. Handoffs are durable notes you promote into memory cards. The evidence ledger is searchable history and receipts, treated as untrusted context rather than instructions.

Does it work with GraphTrail? Yes. GraphTrail covers structural code deltas; MiseLedger covers session and receipt evidence. Together they close the receipts-to-context loop.

Where is the product page? brigade.tools/miseledger. Station CLI: brigade evidence.

Related: GraphTrail / code graph, MCP sync.