Error tracking that ends in a pull request.
Parsemend speaks the Sentry protocol, so the SDK you already installed keeps working. Then an agent reads the stack trace, names the root cause, and opens a draft pull request against the line that threw.
1 line to migrate4 modes to run the agent0 markup on tokens
TypeError: Cannot read properties of undefined (reading 'id')
src/auth/session.ts:142scan fixability 0.92 > threshold 0.80cause auth retry races the session refreshrepro POST /api/session -> 401 -> stale readplan guard session.user before read (+4 -1)
unchanged line: const session = await refreshSession(token)removed line: return session.user.idadded line: if (!session?.user) {added line: throw new AuthRetryError('session invalidated')added line: }added line: return session.user.idFive steps, and you can stop it at any of them.
Each step is a checkpoint with a confidence score attached. A run that dies at step three resumes at step three. A run that is not confident enough pauses and waits for you.
- 01scan
Scan
The issue is scored for fixability. Runs start only above the project's threshold.
- 02root cause
Root cause
The agent reads the context bundle and states, in one sentence, what is actually wrong.
- 03plan
Plan
A change plan, before any code. You can edit it, or reject it, before a line is written.
- 04patch
Patch
The plan becomes a diff. Confidence below threshold pauses the run instead of guessing.
- 05draft PR
Draft PR
A draft pull request, with the root cause in the description. You review and merge.
Four ways to run the agent. Three of them never show us your code.
The fix run is the product. Where it executes, whose model it calls and who pays for the tokens are yours to choose.
Bring your own agent
code stays putYour agents. Our queue.
Parsemend triages errors into a fix queue and exposes it over an API and webhooks. Your own agents, running on your own servers, claim a fix run, do the work, and post the result back. Parsemend never calls a model and never sees your source. You pay for the framework, not for inference.
bring-your-own-agent →Your API keys
code stays putOur loop. Your credentials.
Parsemend runs the fix-run state machine — context bundles, confidence gating, resumable steps — using your own provider credentials. Anthropic, OpenAI, Gemini, or a self-hosted Ollama endpoint. Inference is billed to your provider account at raw token prices, never marked up by us.
your-keys →Local CLI
code stays putThe fix run, on your machine.
Run npx parsemend fix <issue> in the repository. The CLI pulls the context bundle for that issue, executes the fix run locally against your own model credentials, and opens the draft pull request. Your source never leaves the machine — Parsemend only ever sees the error events you already send it.
cli →Managed
repo accessConnect the repo. Read the PR.
Parsemend runs the fix on its own infrastructure with its own model credentials. It needs a GitHub App installation with read access to the repository and write access to pull requests. This is the least setup and the only mode where your source is read by Parsemend's servers.
managed →
The whole tracker, not a demo of one.
The agent is the reason to pay. It is not an excuse for a thin error tracker underneath it.
Sentry SDK compatible
shippedKeep the SDK you already installed. Envelope and legacy store endpoints, all three DSN auth forms, unknown item types tolerated rather than rejected.
Grouping that survives refactors
shippedCustom fingerprint, then in-app frame signatures with recursion collapsed, then exception type and value, then a parameterized message. Many hashes fold into one issue.
Regression detection
shippedA resolved issue that sees a new event flips to regressed. No cron, no sweep — it happens on the write path.
Breadcrumbs and context
shippedThe last N things that happened before the throw, normalized and stored with the event rather than sampled away.
Tags, environments, releases
shippedIndexed as a key/value table, not scanned out of JSON at query time. Filter issues by environment or release without a full-text search.
Rate limits and quotas
shippedPer-key fixed-window limiting that answers with 429, Retry-After and X-Sentry-Rate-Limits, so your SDK backs off the way it already knows how.
Retention by partition drop
shippedEvents live in a range-partitioned table. Expiring a day is a DDL statement, not a mass delete that vacuums for an hour.
Source maps and alert rules
plannedUpload artifacts with debug IDs so minified frames resolve to your source. Route issues to email, Slack or a webhook on the conditions you set.
Two bills, on purpose.
You pay Parsemend a flat fee for the framework: context bundles, the fix-run state machine, confidence gating, PR post-back. You pay your model provider for inference, directly, at their raw token prices. We never resell inference, so we never have a reason to send you a bigger model than the job needs.
Parsemend
flat
A flat monthly fee. It does not move when your error volume spikes or when you switch models.
Your model provider
raw
Whatever the run actually consumed, billed to your account by Anthropic, OpenAI, Google — or nobody, if you run Ollama.
In managed mode there is only one bill, because the tokens are ours. See the pricing breakdown.
How you will know whether it works.
Every fix run is scored against a benchmark suite of real, closed issues with known-good patches. The methodology, the suite and the pass rate are published — including the runs where the agent produced a patch that did not hold.
Results are published with the benchmark methodology rather than quoted as a headline figure. If a number here cannot be reproduced from the suite, it should not be here.
There are no customer logos on this page, and no testimonials, because Parsemend has no customers yet. Putting fake ones here would be the first lie, and there is no good place to start.
What there is instead: the ingest pipeline is documented down to which Content-Encoding values it accepts, the fix-run state machine is described step by step, and the comparison tables cite Sentry's own pages with the date we read them. If something on this site is wrong, mail me and I will change it.
— Vasil Cholakov, founder and engineer
Error tracking is free forever. The agent is why you'll pay.
No credit card for the free tier. Free signups never consume our model tokens.