Issues, code reviews, documents, chat and call transcripts are indexed into one base and answered under your own permissions. Ask the in-app assistant, or give Claude Code or Cursor the same base over MCP, from issue to deploy.
This is the center of Code4: one index over seven sources, answered under the permissions you already have, for your team in the app and for your agents over MCP. Nothing here is a separate product to buy or a wiki to keep alive.
Indexed from
One knowledge base
A keyword pass and a vector pass, merged and expanded along links, answered under your permissions.
Asked from
Seven sources are indexed: chat, issues, code reviews, project documents, call transcripts, commit messages and the code of each default branch. Code on other branches is not indexed; branches come back only as links hanging off a result that already matched.
A question runs a keyword pass and a vector pass at once, the two rankings are merged, and the result is expanded along the links between an issue, the review that closed it and the commits that named it. Take the embedding service away and the vector pass drops out, while the keyword pass keeps answering.
Ask the assistant inside the app, or connect the base over MCP: streamable HTTP, sign-in through Keycloak, and every call runs as you rather than as a service account. The same endpoint carries tools for issues, reviews, branches, pipelines and deploys, so a coding agent reads the base and works in your tracker without a second account.
The base has no input of its own. It fills up from work that would happen anyway: issues, reviews, documents, chat and calls. Pick one to open it in the window at the top of the page.
Custom fields, subtasks, checklists, saved filters and a timer on the issue. Boards with WIP limits, sprints and swimlanes.
Git hosted on the platform. Merge requests with per-line threads, suggested edits that land as a commit, and reviewer approvals.
Pipelines written in Java, Go or TypeScript, or a YAML file. Environments, deploys and rollbacks, and a deploy can wait for a named person to approve it.
Chat and threads next to calls with screen sharing and recording. After a call you get a transcript, a summary and action items with owners, once participants consent.
An assistant on every screen shows each tool call and asks before risky actions. Over MCP, Claude Code or any client gets more than 150 tools and acts with the permissions of the person who signed it in.
Documents in a folder tree with version history. All of the above lands in one index, and an answer names the source it came from.
One issue, from the first message to the call notes. Pick a step to open it in the window at the top of the page.
Kwame posts the Svalbard pass log in Ground segment: SAFE_MODE_EXIT went out twice.
AURORA-T-2 is created from that message, so the log and the thread stay with it.
Lukas opens merge request #14 to keep the original reference on retry. Sofia reviews it.
Build 128 is healthy on staging, and production waits for Priya to approve it.
The incident review call leaves a transcript, a summary and action items, AURORA-T-2 among them.
Code4 works best for 2 to 20 engineers on a new or young project: a studio starting client projects, a startup setting up engineering for the first time, or a product team that already codes with Claude Code, Cursor or Copilot.
Code4 runs hosted today. Your deploys can still land on your own infrastructure.
We run Code4 for you. Sign up and start with a 14-day free trial, then stay on the Free plan or choose a paid one.
Deploy to your own Kubernetes. An agent inside your cluster pulls deploy jobs, so credentials never leave it.
Need Code4 itself on your own infrastructure? Talk to us about your requirements.
A Free plan for up to 5 seats and two hosted plans billed per seat, monthly or annually. Every new organization starts with a 14-day free trial of Business, no card required, and then continues on the Free plan unless you choose a paid one. Paid plans are billed by card through Stripe. Teams in the design partner program use Code4 at no charge during the program and get a founding-partner discount when they move to a paid plan.
Annual billing saves $24 per seat a year on Premium and Business.
For a small team getting started, up to 5 seats.
0 US dollars, free for up to 5 seats
For a growing team that reviews code with AI.
21 US dollars per seat per month, Billed monthly
Billed monthly
19 US dollars per seat per month, Billed annually: $228 per seat a year
Billed annually: $228 per seat a year
For an organization that ships to production often.
29 US dollars per seat per month, Billed monthly
Billed monthly
27 US dollars per seat per month, Billed annually: $324 per seat a year
Billed annually: $324 per seat a year
No, and there is nowhere to write it. The product has no article editor and no wiki section: the index is built from what your team writes anyway, which is chat, issues, code reviews, project documents, call transcripts, commit messages and the code on your default branches. What you decide is whether call transcripts and source code join it at all, and any participant can keep a call out.
One database and one permission model. A question about a decision searches issues, review threads, documents, chat and call transcripts in a single pass, because they are not in four products. Pipelines are typed code in a language you already write, and a YAML file compiles into the same model if you prefer one.
A document or a folder can be closed to everyone except the people you name, and the creator stays on that list. Search runs the same permission check the screens do, and it is built the other way round from most: the filter is assembled before the query and an empty set of permissions returns nothing, so a private document does not surface as a hint to someone who cannot open it.
It answers questions in a chat panel, it comments on merge requests as AI Review, it explains why a pipeline step failed when you ask, it drafts an outline of a code review once an admin turns that on, it writes a summary and a transcript for a call, and it powers search across the organization. It does not autocomplete in an editor. The in-app assistant asks before risky actions, and an agent you connect over MCP acts with the permissions of the person who signed it in.
Only what the AI features touch. The assistant, call summaries and issue drafts send their input to Anthropic, and so do AI code review and explanations of failed pipelines, which are on by default and which an admin can turn off. Speech from calls, voice and video messages goes to Deepgram for transcription, and search uses an OpenAI embedding model, which also receives commit messages and the source code of each repository's default branch: sending that code is on by default, and an admin can turn it off. Everything else stays in our database and our file storage, as the Privacy Policy says. If the embedding service is unavailable, search keeps answering from the keyword pass alone.
Repositories move by pushing them: the remote is an ordinary git server over HTTPS, so git push --mirror is the whole job. Issues and documents have no importer yet, and until one exists the REST API and the MCP endpoint are the way in. They are the same interfaces the app itself uses, so nothing is held back from them. During the design partner program we move your first issues and set up your first pipeline with you, by hand.
Code4 runs hosted today. Your deploys can target your own Kubernetes cluster through an agent that runs inside it, so your kubeconfig never leaves the cluster. If you need Code4 itself on your own hardware, talk to us.
Four known gaps. No importers from other trackers. Documents autosave with a lock rather than letting two people type at once. Call transcription runs in one language, set in configuration rather than picked per call, and there is no way to upload a recording that did not happen here. And it is a web app: layouts collapse for a narrow window, but there is no public mobile app yet.
A small first cohort of teams runs one real project on Code4 at no charge for the length of the program, with one knowledge base that the team and its AI agents share. We help with setup and put your requests first. In return we ask for a short check-in, weekly in the first month and then every two weeks, and honest feedback.
You choose. Move to a plan on the pricing page with a founding-partner discount, or leave and take your data with you. Nothing is charged until you choose a plan.
No. Start with one new project on Code4 and keep everything else where it is. Code4 does not sync with GitHub today, so pick a project that can live in one place.
Your code is in git, so a mirror keeps a full copy at any time. Issues and documents are available through the API, and we export them on request. When a paid subscription ends, our terms give you 30 days to ask for an export.
An agent you connect over MCP works with the permissions of the person who signed it in, so give it the access you are comfortable with. The branch protection rules you set hold for it as for that person. Required approvals apply to merge requests, so restrict push to a branch to make a merge request the only way into it. Protected environments wait for an approval before each deploy. The in-app assistant shows every tool call and asks before risky actions.
Yes. Code4 runs an MCP server: add it to your client, sign in, and your agent works with your permissions across issues, reviews, pipelines, docs and calls.
Sign up with Google or Apple and create your organization. It starts with a 14-day free trial of Business, no card required, and then continues on the Free plan unless you choose a paid one.
Want hands-on help with setup for a new project? See the design partner program
Duplicate telecommands on retried uplinks