Skip to content

Òtítọ́

Independent trust infrastructure for agents and reviewers

Prepared by: Oluwasegun Olumbe
Status: v1.9.2 published to npm, GitHub Releases, and the official MCP Registry
Category: Practical AI governance for developers

A Bashbop Ltd product for teams that want any coding agent to produce evidence a human can trust before merge.

About Òtítọ́

Òtítọ́ is a local-first trust harness for coding agents. It maps repository context before a change, then produces deterministic impact, validation, ownership, and review evidence before merge. It complements model-native agent loops instead of replacing them.

Its command-line and package identity is otito.

See the How It Works visual walkthrough — a layered diagram of the discover → index → context → gate flow.

What's New

v1.9.2 published (2026-09-07)

  • otito is now listed on mcpservers.org; README carries the listing badge.

npm v1.9.2 · GitHub Release · MCP Registry

See CHANGELOG.md for the full history.

Documentation Pack

# Document Description Status
01 Context Foundation Repository inspection, maps, search, context packs, and harnesses Active
02 MCP and Agents MCP tools and agent-facing workflows Active
03 Contributor Governance Protected review, CODEOWNERS, required checks, and merge authority Active
04 Release Readiness SemVer, changelog discipline, CI, and release gates Active
05 Trust-Layer Demo Òtítọ́ as a repeatable review workflow Active
06 Builder-Founder Loop Session rhythm, evidence ledger, governance ladder, and next-action rule Active
07 Harness Thesis & AX The original cost and agent-experience thesis, now subordinate to trust evidence Active
08 Tutorials Integration Codespaces setup and MCP onboarding for tutorials Active
09 Convergence Thesis Intent-vs-diff convergence scoring and receipts Active
10 Usage Dashboard Local usage logging and performance trends Active
11 Determinism Thesis Why model variance is structural and the harness is separate Active
12 Dual-Mode Thesis Probabilistic generation beside deterministic verification Active
13 Prompt Determinism Thesis Why prompt settings do not turn a model into a gate Active
14 Trust Harness Thesis Why independent merge evidence outlasts generic agent orchestration Active
15 Herdr Integration Run Otito context and merge evidence inside persistent agent workspaces Active
16 Clean Code Thesis Clean code as owner files, focused diffs, and gates, not a cleaner agent Active

Context Flow

flowchart LR A[Repo or workspace] --> B[Inspect shape] B --> C[Map files and symbols] C --> D[Build context pack] D --> E[Agent or reviewer] E --> F[Change] F --> G[PR review context] G --> H[Otito gate]

Quick Start

npm install -g @bashbop/otito@1.9.2
otito doctor
otito context "review this change" --path .

npx -y @bashbop/otito@1.9.2 doctor

git clone https://github.com/BASHBOP/otito.git
cd otito
npm ci
npm run ci
node src/cli.js doctor

otito mcp

Prove the deterministic merge gate against the committed valid and adversarial corpus:

otito eval --gate-effectiveness