io.github.koten-ai/zeus-dev-helper
OfficialRelated Servers
Alternatives to io.github.koten-ai/zeus-dev-helper
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI coding agents to conduct Socratic interviews, crystallize answers into immutable specifications, execute staged development, and run automated evaluation and evolutionary loops until convergence.MIT
- FlicenseAqualityDmaintenanceDemonstrates agent-native platform onboarding with human-in-the-loop API key provisioning, plus live usage and rate-limit queries via Anthropic Admin APIs.3-
- AlicenseBqualityBmaintenanceLocal-first Agent OS that wraps Claude Code, Codex CLI, and other coding agents in a replayable Seed → Ledger → Runtime contract, driven by an interview → seed → execute → evaluate → evolve workflow loop.346,385MIT
- AlicenseAqualityBmaintenanceKeeps AI coding agents current on Zcash by serving dated, sourced facts, testnet-verified recipes, a stale-pattern and privacy lint, and live transaction status checks without ever touching keys or funds. Agents can also read the bundled llms.txt and follow a guided builder prompt so generated code works on today's NU7 testnet.4MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI coding agents to run a specification-first workflow through MCP tools: Socratic interview, immutable seed specification, execution, staged evaluation, and evolutionary loops. This helps turn vague ideas into verified, working codebases across multiple runtimes.MIT
- AlicenseNot gradedqualityCmaintenanceEnables conversational management of a small invoicing SaaS — customers, offers, invoices, payments, open items, reports, and exports — while capturing missing feature requests, clarifying and assessing them, producing development offers, and triggering a local coding agent to create draft PRs for human review.MIT
TDQS
Scored across 17 tools
The many 'is it green?' tools overlap heavily in spirit—readiness_check, smoke_test_zeus, smoke_test_agent, website_green, and doctor all verify some aspect of the setup—and set_prereq vs load_process_login both handle credentials, so an agent must lean on dense descriptions to choose correctly. The descriptions do carve out distinct roles (platform gates vs describe vs one LLM turn vs catalog page), which keeps this from being worse.
Nearly every tool follows a snake_case verb_noun pattern (start_project, set_prereq, smoke_test_zeus, inject_business_rules, bind_contract). The lone outlier is the bare noun 'doctor', a minor deviation from an otherwise predictable convention.
At 17 tools this sits just in the heavy end of the range for what is essentially a guided dev-helper workflow, and several near-duplicate verification tools inflate the count. Each broadly maps to a step, but consolidation of the check tools would tighten the surface.
The set covers the full first-app lifecycle: prereqs/login, readiness, sampling and scaffolding, business-rule injection, smoke tests, UI green check, error diagnosis, support bundling, and contract binding. Minor gaps remain (no teardown/reset of samples, no project-listing or log-streaming operation), but agents have workarounds.