Project Tiny Context Harness

Project Tiny Context Harness

[](https://www.npmjs.com/package/project-tiny-context-harness) [](https://github.com/Seven128/project-tiny-context-harness/actions/workflows/package.yml) [](https://securityscorecards.dev/viewer/?uri=github.com/Seven128/project-tiny-context-harness) [](LICENSE) [](https://codespaces.new/Seven128/project-tiny-context-harness)

Translations: [Chinese (Simplified)](README.zh-CN.md)

Project Tiny Context Harness is repo-native project memory for AI coding agents, plus a narrow delivery harness with an automatic lightweight route and an explicit machine-assurance route. The product principle is: keep the memory, drop the ceremony. It adds durable project memory behind `AGENTS.md` without becoming an agent scheduler or Git orchestrator. It is designed to reduce drift between large plans, durable project truth, design intent, implementation and proof by keeping ownership recoverable and assurance proportional to the delivery.

Public launch surfaces are English-first; localized documents are secondary entry points.

Best for:

• repositories where coding agents repeatedly rediscover project intent;
• teams using multiple agents or frequent fresh chats;
• maintainers who want durable Context and, when needed, explicit machine-traceable delivery evidence.

Not for:

• replacing project tests, review, CI or human acceptance;
• autonomous Tiny Context execution;
• codebase semantic indexing or external docs retrieval.

Concrete shift:

Before: ask a fresh agent to read the r