Coding agents write features in minutes — but who verifies every commit? Full test suites are too slow to run per commit, so most verification happens late (or never). Koda closes that gap: on every commit it verifies only what changed, in seconds-to-minutes, and remembers what keeps breaking so your agent stops reintroducing old bugs.
Koda never writes code. It orchestrates verification, remembers patterns, and reports — to both the human and the agent.
The three surfaces
Surface
Responsibility
Activation
Core + CLI
Verification, reports, memory, git hooks, CI generation
Ambient status bar, report viewer, one-click enable, Git watching
User clicks Enable
How it works — the pipeline
git commit
│
▼
pre-commit ── secret guard (blocks committed API keys / private keys)
│
▼
post-commit ── koda run (background, never blocks you)
│
▼
1. Read diff ──────────── classify files: api / page / component / lib / config / test
2. Impact analysis ────── agent-supplied (MCP) → Groq fallback → deterministic heuristics
3. Kane browser flows ─── headless, scoped to changed UI only (page/component changes)
4. Endpoint checks ────── GET / HEAD / OPTIONS only; regressions flagged (200 → 500)
5. Integration tests ──── Jest / Vitest / Mocha / node:test, matched to changed files
6. Report ─────────────── JSON (agent-readable) + Markdown (human-readable)
7. Memory ─────────────── recurring patterns, resolution history, time-to-fix
Most commits never launch a browser: API/config/test-only changes verify with endpoints + tests in seconds. Browser flows fire only when UI files change.
Quick start
npm install -g koda-verify
cd your-project
koda init # creates .koda/, installs git hooks, detects your app's port
koda doctor # verifies: git, config, Kane CLI, target URL, directories
Then just keep committing — verification runs in the background on every commit.
One-time browser setup (optional, per user)
Browser flows are powered by the Kane CLI. The IDE extension onboards it for you: click Enable and Koda offers to install Kane and connect your account. Or do it manually:
npm install -g @testmuai/kane-cli
kane-cli login --oauth # opens your browser — use (or create) YOUR OWN Kane account
About Kane accounts — yours, not ours
Koda ships zero credentials. Every Koda user authenticates their own Kane account:
The extension's OAuth flow opens the Kane login in your browser; new users register there
Your session lives locally in ~/.testmuai/ on your machine — never synced, never proxied
Browser-flow credits come from your Kane account, not the developer's
In CI, each repo configures its own KANE_USERNAME / KODA_ACCESS_KEY-style secrets
No Kane? No problem. Koda runs in degraded mode: endpoint checks, integration tests, memory, and reports all work; browser flows are honestly marked SKIPPED — never faked.
Target URLs — localhost, LAN, or hosted
Koda verifies whatever your app points at. The default is auto-detected at koda init (probes common dev ports: 3000, 5173, 8080, 8000, 4200, 5000…). Override it three ways:
koda target https://myapp.vercel.app # permanent — hosted URL, https auto-detected
koda target 192.168.1.5:8080 # LAN IP, http auto-detected
koda run --target https://preview-123.example.com # one-off run
KODA_TARGET=https://staging.example.com # per-session / CI via env
koda run [--project <path>] [--commit <sha>] [--target <url>] [--max-flows <n>]
Verify a commit now
koda report
Show the latest report
koda memory
Dump project memory (patterns, history, fixes)
koda target <url>
Validate, save, and health-check a new target URL
koda cicd [--force]
Generate a validated GitHub Actions workflow (refuses overwrite)
koda doctor [--kane]
Environment check; --kane empirically probes the Kane schema
koda mcp
Start the MCP server (stdio)
Agent integration (MCP)
claude mcp add koda -- npx koda-verify mcp
Works with any MCP client: Claude Code, Cursor, Codex, Gemini CLI, Windsurf, Zed. In a development checkout: claude mcp add koda node /absolute/path/to/koda/mcp/server.js.
MCP tools
Tool
Purpose
koda_verify
Run focused verification. The agent supplies its own impact analysis (flows, endpoints, target, commit, max_flows) — it already read your code, so no LLM cost and no guessing. Groq is only a fallback for non-MCP runs
koda_report
Latest full JSON report — verdicts, coverage, evidence paths
agent edits code → commits → hook fires koda run → report written
→ agent calls koda_verify (its own flows) / koda_report via MCP
→ reads the verdict → fixes what failed → commits again
→ memory marks the failure RESOLVED (with time-to-fix recorded)
Reports record analysis_source: 'agent' when the agent supplied flows — verifiable proof the loop is agent-driven.
Reports
Every run writes a timestamped pair to .koda/reports/:
The JSON includes: commit metadata, analysis_source (agent / llm-fallback / fallback), risk level, per-check results with evidence file paths, memory context (similar failures, patterns, fix confidence), and action_required with priority and suggested focus. Markdown renders PASS / FAIL / SKIPPED distinctly with coverage status.
Raw Kane session events are preserved per-flow under .koda/evidence/.
Memory — remembers what keeps breaking
Every failed check gets a stable key; failures that recur 2+ times become patterns
When a fix lands and the check passes, the failure is marked resolved with time_to_fix_ms
Coverage-gap findings ("no tests cover app/page.js") resolve automatically once a passing test covers those files
Skipped checks (app offline) never pollute memory
Writes are atomic; corrupt memory files are quarantined, not deleted
Safety guarantees
Non-destructive hooks — existing pre-commit/post-commit/pre-push hooks are backed up before appending; Husky respected; idempotent via marker
Read-only HTTP by default — only GET / HEAD / OPTIONS; mutating methods require explicit opt-in (allow_mutating_methods: true) plus agent-declared endpoints
Honest results — if the app is down, checks are SKIPPED, never reported as failures; skipped checks never enter memory
No secrets shipped — the package contains zero credentials; the pre-commit guard blocks accidentally committed keys
CI/CD
koda cicd
Generates .github/workflows/koda.yml from a validated template: Node setup, npm ci, build-if-present, Kane CLI install + auth via GitHub secrets (KANE_USERNAME, KANE_ACCESS_KEY), app start, wait-on target, koda run --commit ${{ github.sha }}. Template-first — no LLM-generated YAML. Refuses to overwrite without --force.
