5 parallel AI review passes. Every dismissed finding makes the next review sharper. Code quality compounds over time.
uv tool install git+https://github.com/fabioesposito/superseded
Requires Python 3.14+ and at least one AI CLI (claude-code, opencode, or codex).
Most tools treat every review like the first. Superseded learns from every decision and tailors each pass to your code.
Dismiss a finding once and it's gone. Superseded remembers so the same noise never resurfaces.
Every dismissal sharpens the next review. Your team's judgment compounds into a higher-quality signal.
Security, correctness, performance, style, and architecture — each with its own prompt, running in parallel.
Dismiss a finding once. Superseded remembers. The next review avoids that noise. Code quality compounds with every PR.
5 AI passes analyze your diff in parallel with domain-specific prompts.
Mark a finding as noise with one click. Add context if you want.
SQLite memory stores the decision and reasoning, scoped to your repo.
Next review injects dismissed findings as negative context. Noise drops.
Each pass gets a targeted prompt and runs concurrently. Findings merge and deduplicate automatically.
Injection, auth, secrets, crypto, supply chain
Logic errors, edge cases, error handling
N+1 queries, memory, caching, complexity
Naming, conventions, readability, patterns
Coupling, boundaries, abstractions, tech debt
Each agent executes inside an ephemeral microVM — a private filesystem, a private kernel, a hard boundary. Choose Docker Sandboxes (sbx) on Linux/KVM, or smolvm (embedded smolmachines SDK) on macOS, Linux, or Windows. Your host is never touched, and nothing leaks between reviews.
A fresh sandbox spins up for every PR. No shared state, no leftovers.
Private filesystem and kernel. The agent cannot reach your machine.
Docker Sandboxes (sbx, Linux/KVM) or smolvm (smolmachines SDK, macOS/Linux/Windows).
The sandbox is destroyed after the review. Nothing persists.
CLI for local dev. GitHub Actions for CI. Server mode for multi-repo. Memory that improves over time.
Post findings as inline PR review comments. Critical issues request changes. Uses gh CLI.
Use Claude Code, OpenCode, or Codex. Choose per-review or configure a default.
Composite Action POSTs to your review server. No agents or secrets in CI — the server does the work.
Self-hosted GitHub App. Multiple repos, webhook-driven, configurable concurrency.
JSON for piping, markdown for docs, terminal table for quick scanning.
Auto-detects linters (ruff, mypy, eslint, tsc, bandit, gitleaks, go vet) and injects signals before AI review.
Run superseded skill install once and Claude Code, OpenCode, and Codex invoke superseded directly — no more “I don’t recognize that tool” detours.
Install and run your first review.