
Codna — repository intelligence
io.github.thyn-aiPublished by GitHub account thyn-aiv0.2.113Updated Nov 8, 2026
Repo intelligence: triage, fix PRs, SARIF reachability, recall. Free codna login to execute.
Overview
Codna gives an assistant repository intelligence: triage issues to suspect files, plan fixes, check SARIF findings for reachability, and recall code from…
- What you can do
- Triage a repository and locate code relevant to an issue, deterministically and without LLM tokens
- Prove which SARIF scanner findings (CodeQL, Semgrep, Snyk, Trivy) are reachable, read-only
- Recall code from on-device memory with semantic and lexical search, fully offline
- Root-cause and plan a fix, read-only by default, or push a branch and open a real pull request
- File a bug, feature request or question to the vendor's feedback repository
- When to use it
- Useful when an assistant works inside a codebase and needs to find the files behind a bug report, judge whether a scanner finding is actually reachable, retrieve relevant code from local memory, or produce a fix and optionally a pull request.
- Requirements
- Local Python package (pip, pipx or uv) on Python 3.12-3.13, macOS Apple silicon or Linux x86_64, with git on PATH; runs as a stdio server. A one-time free codna login is required to execute any tool. codna_fix also needs a provider key such as ANTHROPIC_API_KEY, OPENAI_API_KEY or GEMINI_API_KEY; open_pr=true and codna_report_bug need GITHUB_TOKEN.
Installation
In SourceWeft
- Open Codna — repository intelligence in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Codna
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.
Install
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:
Commands
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.
MCP server
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:
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
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.
What leaves your machine
- Repository mapping, triage, recall and
impactrun offline. No model is involved. fixandreviewsend one issue-specific evidence bundle to the provider you chose, under your key. Not the repository.- Secret redaction is always on and cannot be turned off.
privacy.egress: fail-closedincodna.yamlrefuses to run tests without network denial and skips registry lookups during review.- Source distributions exclude runtime binaries, keys,
.envfiles and logs.
Links
- Homepage: https://codna.ai
- Documentation: https://docs.codna.ai
- Source (public mirror): https://github.com/thyn-ai/codna-cli
- Security: https://codna.ai/security
Source: README.md at commit f8cd448
Tools
0Version history
16- v0.2.112Nov 7, 2026
- v0.2.106Nov 6, 2026
- v0.2.104Nov 5, 2026
- v0.2.98Nov 5, 2026
- v0.2.97Nov 5, 2026
- v0.2.96Nov 1, 2026
- v0.2.95Oct 26, 2026
- v0.2.94Oct 16, 2026
- v0.2.93Oct 11, 2026
- v0.2.90Sep 28, 2026
- v0.2.89Sep 25, 2026
- v0.2.87Sep 24, 2026
- v0.2.86Sep 24, 2026
- v0.2.85Sep 23, 2026
- v0.2.84Sep 23, 2026
- v0.2.83Sep 23, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts