Jan by Menlo Research

# Fix list: Jan

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/jan, the October 2026 research run, assessed 3 October 2026. Grade D, 51.4 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Jan: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Security & auth, 43 out of 100, up to 10 more on the total

Why it scored 43: Read with the tool checklist. One optional key typed into Settings, empty by default, accepted as `Authorization: Bearer` or `X-Api-Key`, with no scopes, names or keys per client. `jan serve --api-key` defaults to empty too (10). The app asks before each MCP tool call by default, with an allow-all switch, and server-side tool execution through the API is off by default. The key can't be limited, and in 0.8.4 a 0.0.0.0 bind drops the Trusted Hosts list (11). The docs advise a key when binding to 0.0.0.0 but say nothing on injected instructions in tool results, and the cap on tool-result size is only on main (5). Verbose server logs are on by default with a Server Logs view (10). A security policy with a 48-hour acknowledgement, reports through Discord or a Google form and credit for researchers, but no bounty, no security.txt at jan.ai and no published advisories, though the fix commit names GHSA-x6p8-7cp8-c3p6. The 0.7.2 notes disclosed a happy-dom sandbox fix in October 2025, and NVD lists no CVE for Jan under janhq or Menlo (7).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 2. Agent ergonomics, 46 out of 100, up to 8.8 more on the total

Why it scored 46: Read with the API lines. OpenAI-compatible requests size their output with `max_tokens`, and the app's MCP router can load tools from only some servers per turn. The cap on MCP tool results is only on main so far (15). `GET /models` lists everything, with no paging or filters (8). Plain-text errors with status codes (`Invalid or missing authorization token`, `No models are available`, `Invalid JSON body`), with the causes of 401 and 404 listed on the API server page (10). Stateless chat completions are safe to repeat. No retry or idempotency guidance (6). The defaults suit a local caller (127.0.0.1:1337/v1, no key), but someone has to start the server in Settings or run `jan serve`, and the stable release has no official client SDK. Any OpenAI or Anthropic SDK works (7).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 3. Schema & documentation, 56 out of 100, up to 7.2 more on the total

Why it scored 56: Read with the API lines. The server serves an OpenAPI 3.0 file at /openapi.json with a Swagger page at /, covering 4 paths (models, chat completions, messages, orchestrations) with typed schemas and a bearer scheme, but only 200 responses, and /completions, /embeddings and /messages/count_tokens aren't in it. The spec on the docs site is the retired Cortex API (12). No llms.txt at jan.ai or www.jan.ai (404 on 3 October), and no Markdown copies of pages found (0). The API server page explains each setting and when to change it (127.0.0.1 or 0.0.0.0, the key, CORS for browser clients, server-side tool execution) (12). Request schemas in the spec mark required fields and use enums, while the extra llama.cpp parameters and errors are described only in prose (10). One curl example, and a troubleshooting list for connection refused, 401, 404 and CORS errors. Error bodies are plain text (9). A /v1 prefix, semver releases and a dated changelog with GitHub release notes (13).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 4. Reliability, 68 out of 100, up to 6.4 more on the total

Why it scored 68: Read with the local-software lines, since Jan runs on the owner's machine with no hosted service behind its API. Installers for macOS 13.6 or later, Windows 10 or later and Linux (.deb and AppImage), plus Flathub and the Microsoft Store, with requirements in the README and the install guides (20). The Linter & Test workflow runs the web app's tests and Rust coverage on every push to main (370 TypeScript test files and 3,377 Rust test functions), and the runs on main our reader saw, from 1 and 2 October, passed. We read the run list, not each run (22). 409 open issues and 133 open pull requests. The newest open issues our reader saw (24 and 25 August) carry labels and a 0.8.5 milestone, and a stale bot closes issues after 180 days without activity (15). Semver tags, a dated changelog per release with a Migration section in 0.8.4, and GitHub release notes, but a security fix has waited on main since 24 July for a release (11). 0.8.4, pre-1.0 (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 5. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: Self-hosted rule. No x402, MPP or L402 (0). Free and Apache-2.0 with no account, card or anything to buy, so 20, 20 and 20 on the last three lines. Cloud models are paid to the provider with the owner's key.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 6. Maintenance & community, 47 out of 100, up to 4.6 more on the total

Why it scored 47: 0.8.4 on 23 July 2026, 72 days before this check (20). One release in the last 90 days. Notes for 0.8.5 are drafted in the docs source, dated 22 September and unpublished, and the repository's Flatpak manifest moved to 0.8.5 on 2 October (0). 151 commits on main's first-parent line since 4 July, 98 of them in the last 30 days, and new issues get labels and milestones, but we couldn't see reply times (15). No MCP registry entry and no SDK in the stable release. Python and TypeScript agent SDKs exist in nightly builds (3). A Dependabot config, CI on every push to main and a pinned Rust toolchain (9).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 69 out of 100, up to 2.7 more on the total

Made of editorial 66, provenance 72.

Why it scored 69: Apache-2.0 for the app, the server and the CLI (30). The privacy policy (Menlo Research Pte Ltd, last updated 16 January 2025) says analytics are opt-in, tied to a random ID, sent to PostHog EU and kept up to 12 months. A second privacy page still names Cortex, a retired engine, and says usage logs never leave the computer. Neither mentions the update check to apps.jan.ai or that new model downloads from Hugging Face go through Menlo's mirror at apps.jan.ai first (14). No deprecation policy. The 0.8.4 notes have a Migration section and keep the old settings for a downgrade (6). Analytics are asked for at first launch and off until accepted (the code opts out by default, turns off autocapture and session recording and strips URL properties), with a toggle under Settings, Privacy. The update check and the download mirror aren't disclosed (16).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: jan.ai, registered 2017-12-16 (8 years) (11 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 2026-07-24. GHSA-x6p8-7cp8-c3p6. In 0.8.4, the current release, binding the Local API Server to 0.0.0.0 replaces the Trusted Hosts list with a wildcard, so any Host header is accepted and any Origin reflected with credentials allowed, which with the default empty key lets any web page the owner visits call the server. The fix landed on main on 24 July 2026, no release carries it 71 days later, and the advisory isn't published. It needs a setting the docs flag as risky, -4. https://github.com/janhq/jan/commit/3e1c1e724f696620d89bb4a9cc18a380e0753757

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- When 0.8.5 ships. Its notes are drafted and dated 22 September 2026 but unpublished on 3 October
- Whether GHSA-x6p8-7cp8-c3p6 will be published. The fix commit and the draft notes name it, the advisories page doesn't
- Reply times on issues and pull requests, which we couldn't read from the issues page
- What Menlo's mirror at apps.jan.ai logs about downloads. Neither privacy page covers it
- We found no terms of use for the app or jan.ai

## Weaknesses

- No release since 0.8.4 on 23 July 2026, while a security fix waits on main
- One optional API key with no scopes, empty by default
- In 0.8.4 a 0.0.0.0 bind ignores Trusted Hosts and reflects any Origin (GHSA-x6p8-7cp8-c3p6)
- New Hugging Face downloads go through Menlo's mirror at apps.jan.ai, which neither privacy page mentions
- No llms.txt, plain-text error bodies, and the OpenAPI file on the docs site is for the retired Cortex API

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Ask the owner to start the server (Settings, Local API Server) or run `jan serve`. Nothing listens until then
- Call http://127.0.0.1:1337/v1 for the app and localhost:6767/v1 for `jan serve`. The ports differ
- Read /openapi.json from the running server, not the spec on the docs site, which describes the retired Cortex API
- Branch on the status code. Error bodies are plain text
- Keep the bind at 127.0.0.1 on 0.8.4. Trusted Hosts is ignored on 0.0.0.0 until the next release

## What the review panel asked for

- a release with the fix
- a published advisory
- release the Trusted Hosts fix
- publish the advisory

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.