l0ng-ai
Featured
tty7
tty7 is a fast, GPU-accelerated terminal workbench with persistent sessions, built-in input tools, SSH support, and coding agent awareness.
bathos
BATHOS turns a single Claude Code session into a structured product team with 17 specialist roles, a 7-wave pipeline, scale-adaptive routing, and hard quality gates, all enforced by a deterministic Rust engine.
Stars
22
7-day growth
No data
Forks
12
Open issues
1
License
NOASSERTION
Last updated
2026-07-23
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It directly addresses the context drift and lack of verification in single LLM conversations by imposing a rigorous, gated workflow with independent roles and a tamper-evident audit chain, enabling one person to drive a full product development process.
Who it is for
- Developers using Claude Code who want structured AI-assisted development
- Solo developers building products end-to-end
- Teams seeking a methodology to enforce quality gates and traceability
- Organizations evaluating AI workflow agents for regulated or high-stakes projects
Use cases
- Building a new service from scratch with full discovery, design, and verification
- Adding a complex feature to an existing project with independent review
- Conducting a thorough design-review-implement-verify cycle for a product
- Prototyping and validating an idea with structured market research and architecture
Strengths
- 17 specialist roles with independent reviewers (e.g., Matthew the story engineer, Thomas/Matthias) and a hard readiness gate that physically blocks implementation on FAIL
- Scale-adaptive routing (Lv0–4) matches effort to task size, avoiding unnecessary overhead
- Dogfooding evidence: the project built itself and an independent review caught blocking defects the author missed, validating 'generation ≠ verification'
- Deterministic Rust engine enforces invariants, gate verdicts, and a tamper-evident audit hash chain
Considerations
- Depends on Claude Code's experimental Agent Teams feature, which may change or be unstable
- Not yet production-hardened – v0.2.0 early stage with APIs and commands subject to change before 1.0
- Some wave commands are orchestration prompts run manually by the lead, not fully autonomous flows
README quick start
Quick start
Description
AI Workflow Agent method of overwhelming depth — 18 specialist roles, a 7-wave delivery pipeline, scale-adaptive routing, and hard quality gates, backed by a small Rust engine that makes the critical invariants deterministic instead of vibes.
Related repositories
Similar projects matched by category, topics, and programming language.
steelbrain
Featured
reims-vgpu
reims-vgpu is an experimental virtual GPU for macOS guests that uses QEMU to decode the guest's GPU command stream and execute it through Metal or Vulkan, leveraging the built-in AppleParavirtGPU driver without requiring custom kexts.
m-novotny
Featured
memguard-rs
A Rust library that provides secure memory handling primitives including zeroization on drop, memory locking, constant-time comparison, and compile-time guarded regions, with zero dependencies and no_std support.