open-source tools
for agentic composition.
Local-first building blocks for agent-driven workflows. Memory across sessions, signed code review, whole-codebase audits, and browser views for any CLI — pieces small enough to compose, opinionated enough to ship.
// the suite
think
@openthink/thinkKeeps every agent you run aligned with what's been decided, done, and learned — one shared, local-first memory, recalled before the agent acts, on every machine you own.
stamp
@openthink/stampAuthor-agent opens a diff. Reviewer-agents you control return signed verdicts. The gate stays closed until they approve, and the attestation verifies downstream — at a self-hosted gate, on a GitHub PR check, or local-only.
ui-leaf
@openthink/ui-leafCustomizable browser views, on demand, for any CLI in any language. Mount a template once with a single command; ship the data — get a rich rendered view.
audit
@openthink/audit · oauditComposable audit specs for cross-cutting passes — security, perf, dead code, doc drift. Spec docs in trusted/untrusted pairs; one long-lived agent per pass. Built in Rust.
// the shape of it
Each tool stands alone. Each tool composes with the others. stamp reviews the diff before merge; think remembers what was decided so the next session doesn't repeat the work; audit sweeps the whole tree on demand; ui-leaf renders any of it in a browser when a terminal isn't enough.
All local-first. All MIT. No mandatory cloud. No vendor lock-in. The pieces are small on purpose — pick the ones you need, leave the rest.