alexcinovoj.devby TechTide AI
Contact
Back to resources
Open-source project

TechTideAI2

TechTideAI2 separates agent decisions, application data, and audit output. It uses explicit state transitions, execution timeouts, and adversarial evaluation tests.

Project details

Classification
Open-source project
Repository
Alexi5000/TechTideAI2
Language
TypeScript
License
MIT
Status
Active development
Tests
3 test notes
Last verified
2026-08-01

What it is

I use TechTideAI2 to separate decisions, application state, and audit output. Agent runs follow explicit state transitions and execution timeouts. The repository includes contracts and an evaluation workflow you can inspect. Its demo walkthrough does not describe a customer deployment.

Architecture

  • Separate components handle decisions and policy, application state, and audit and evaluation output.
  • Explicit state-machine transitions per agent run instead of open-ended loops.
  • Hard execution timeouts at the runtime boundary.
  • Adversarial evaluation tests run from a separate workflow; inspect the suite for its current coverage.
  • Fastify and LangChain/Mastra on the service side, React front end, Supabase data plane.
Control flow
  +----------------+   +----------------+   +-----------------+
  | control plane  |   | data plane     |   | evidence plane  |
  | policy, state  |-->| app state      |   | audit + evals   |
  | machine, gates |   | supabase       |-->| golden suite    |
  +-------+--------+   +----------------+   +--------+--------+
          |                                          ^
          +------------------ traces ----------------+

Tests and gates

  • Four workflows: ci, pr, evals, and notebooks. Evals run separately from unit CI.
  • The README describes the reference evaluation suite, which runs through the evals workflow.
  • Contracts and database directories are versioned alongside the services.

Limits

  • The reference suite checks regressions in selected tasks. It does not compare performance with other platforms.
  • Separating components does not establish compliance with any specific regulation.
  • Demo walkthrough content in the repository is illustrative, not a customer deployment.

Source files and examples

Related methods

Acceptance tests for agent work

Executable checks test the task and detect regressions.

Evaluation tests for releases

A fixed evaluation suite checks release requirements.

MCP tool permissions

The server checks which tools a caller may use.

Recording agent runs

A shared trace ID connects the records of a run.

Spending limits for agent runs

Budget checks run before provider requests.

Pausing for human approval

The run waits for approval before the action executes.

Related projects

ClawKeeper

ClawKeeper checks proposed Claude agent actions against explicit rules before a model call. Autonomous spend defaults to zero, and the database enforces an append-only audit log.

TechTide Harness Kit

TechTide Harness Kit uses JSON Schema to declare skill permissions, risk tiers, network access, and approval requirements. Automated checks validate declarations and run prompt-injection fixtures.

CipherClaw

CipherClaw analyzes recorded agent activity without model calls. It builds causal graphs, scores possible causes, and flags failure patterns.

Swarm 357

357 Claude agent roles across six business layers, with portable memory, enforced cost caps, a bash policy gate, and durable checkpoints.

I document the project here. TechTide AI publishes current service scope, prices, and terms.

Critical System Implementation at TechTide AI
Back to top
Talk to Alex
alexcinovoj.dev

© 2026 Alex Cinovoj · TechTide AI · Columbus, OH