The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Codna — repository intelligence listing page.
Understand. Fix. Evolve.
Agents read your code. Codna understands it.
Codna maps a repository before it spends a token. It then reviews pull requests, fixes bugs and
proves which scanner findings are reachable. The same codna command runs on your machine, in the
GitHub Action and behind the GitHub App.
Runs on your machine or your cloud. Your code never leaves without your key.
Python 3.12–3.13. Wheels for macOS on Apple silicon and Linux x86_64. git on your PATH.
Nothing else to install: no Node, Bun, Docker or server. The agent runtime ships inside the wheel.
Local commands need no Codna key. fix and review use your own model provider key, stored in
the OS keychain and never printed:
codna fix prints the root cause, the impacted symbols, the blast radius, its confidence and a
regression risk. --open-pr needs a git URL and a GitHub write token. codna review posts one
inline comment per finding with severity, category and a suggestion block, and an Approve when the
diff is clean at medium and high. codna secure reads SARIF 2.1.0 from CodeQL, Semgrep, Snyk,
Trivy or any other scanner.
Other commands: init, status, doctor, login, key, impact, memory export, report.
Full reference: docs.codna.ai/reference/cli.
Run Codna as a Model Context Protocol server over stdio — the same engine the CLI uses, inside Cursor, Claude Desktop, or your own agent:
Five tools, each returning JSON; a failure comes back as codna_<tool> error: … text and never
crashes the server:
| Tool | What it does | Needs |
|---|---|---|
codna_triage | Understand a repo and locate the code relevant to an issue. Deterministic, 0 LLM tokens. | free codna login |
codna_secure | Prove which SARIF scanner findings (CodeQL, Semgrep, Snyk, Trivy) are reachable. Read-only, 0 LLM tokens. | free codna login |
codna_recall | Recall code from local on-device memory — semantic + lexical search, fully offline. | free codna login (which also installs the on-device runtime) |
codna_fix | Root-cause and plan a fix (read-only by default); with open_pr=true pushes a branch and opens a real PR. | free codna login + provider key (BYOK; + GITHUB_TOKEN for open_pr=true) |
codna_report_bug | File a bug, feature, or question to thyn-ai/feedback. | free codna login + GITHUB_TOKEN (else returns a pre-filled URL) |
Introspection (initialize/tools/list) needs no credentials. Executing any of the five tools
requires the one-time free community login (codna login — device authorization, free community
license) — fully offline thereafter. codna_fix additionally needs a provider key (BYOK, e.g.
ANTHROPIC_API_KEY); codna_report_bug needs GITHUB_TOKEN or it returns a pre-filled issue
URL; codna_recall additionally uses the on-device memory runtime that the same codna login
installs.
Full reference:
docs.codna.ai/guides/mcp.
Code memory and recall run on your machine after a one-time free codna login (device
authorization), which also installs the signed on-device runtime. From then on, recall runs fully
offline: no key, no network calls. The optional
codna[memory] extra adds the on-device semantic reranker; without it, recall ranks lexically.
impact run offline. No model is involved.fix and review send one issue-specific evidence bundle to the provider you chose, under your
key. Not the repository.privacy.egress: fail-closed in codna.yaml refuses to run tests without network denial and
skips registry lookups during review..env files and logs.