compound + forge
Popular repositories Loading
-
case-code-review
case-code-review PublicAI code review CLI that checks a change against the contracts around it — function-level review units; caller/callee/owner/used context from authored specs (spec-case) and docstrings (zero adoption…
Go 3
Repositories
- chat-tui Public
Chat/agent UI components for the terminal, built on opentui — view models in, intents out
- reqloop Public
- devloop Public
A guard-railed, closed-loop workflow for AI coding agents: live state bus + execution-level hard intercepts for Claude Code and Codex (GitHub PR / GitLab MR). From step-level to requirement-level; eval-driven, spec-driven, human-in-the-loop.
- case-harness Public
- hostel Public
An agent-native sandbox runtime: run many isolated sandboxes (beds) from one process, with an OpenSandbox-compatible HTTP API.
- case-code-review Public
AI code review CLI that checks a change against the contracts around it — function-level review units; caller/callee/owner/used context from authored specs (spec-case) and docstrings (zero adoption); cross-repo rules via fqn. Built on open-code-review; OpenAI & Anthropic compatible.
- spec-case Public
Co-located spec/case/rule/link markers on functions and types (Go doc-comments / Python decorators) + specgen → spec.json. Symbol-id (in-repo) & fqn (cross-repo) identity, so review tools like case-code-review inject a symbol's contract wherever it's changed, owned, called, or used.
- go-stdx Public
Go stdlib extensions — admitted only when the standard library doesn't offer it. Zero dependencies, rule of three.
- skill-plus Public
A backward-compatible extension to the Agent Skills format: add a flow (stages) and soft/hard rules to a skill, with stage-scoped just-in-time context injection. LLM-guided, not strictly executed. (skill v2, spec-first)
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…