Fable Mode
Mechanical write gates, evidence receipts, and adversarial review for AI coding agents.
按你想完成的任务或你使用的应用搜索,再按分类筛选。
按搜索词在名称、描述和分类中出现的数量排序,其次按星标数。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Mechanical write gates, evidence receipts, and adversarial review for AI coding agents.
Evidence-oriented code questions, diff review and test selection via a Jev endpoint.
Strict AI code reviewer powered by Groq. Finds bugs and vulnerabilities.
Semantic code graph: 42 tools, 38 languages. Callers, impact, AI context, memory, PR review.
Local, deterministic review of Git changes: weakened tests and CI gates, risky flows, blast radius.
Multi-model AI orchestration MCP server with code review, compare, and debate tools.
Godot 4.7 for coding agents: offline API, checks, review, safe edits, tests, play, 3D models.
Deterministic guardrail your coding agent runs on itself: diff-scoped findings, zero LLM tokens.
Audit infrastructure for AI coding agents with evidence-backed review and policy gates.
Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.
Code review service, delivered per API call as an atom service on Conduit Atoms.
MCP server for PR code review, commit messages, changelogs, and secret detection.
Autonomous coding pipeline: frontier models plan and review, open-weight models write the code.
Repo-native task continuity for AI coding agents: a reviewed task-state ledger served over MCP.
Security + bug + perf + refactor audit for Python. Returns 0-10 score + MD report.
AI code review for GitHub PRs with an MCP autofix loop for Claude Code and Cursor
AI code review — security, quality, performance. Learns your patterns. Receipted.
Evidence-chain whiteboard for AI research agents: every claim traces back to its run and code.
Live PR/MR code reviews via review_url_code. OAuth or portal Bearer auth.
Contract-driven cross-host agent handoff, code review & verification harness via MCP & SQLite WAL
Tently, the AI PR reviewer for GitHub: agents check team decisions before they write code.