Chata nechero GitHub Repo

Izvi ndezvekodzero-aware chat iyo inoisa yose codebase uye inokutendera kuti ubvunze mibvunzo nezvei muChirungu chaiyo. Peta webhusaiti yeGitHub repo URL (kana kurodha mafaera ako) uye AI inoverenga chirongwa, uyezve inobvunza zvinhu senge "kwaiitwa sei auth?", "zvinoratidza sei izvi", " nei izvi zvisiri kushanda?", kana "izvi zvinonzi sei izvi API?" — neruzivo rwemafaira echokwadi. Chii chinonzi pairi-kurongwa nemunhu anenge averenga yako yose repo.

Maitiro maviri. (1) Peta repo URL (e.g. https://github.com/owner/project) uye tinya Load — isu ticha clone uye index the source. (2) Drag-and-drop yako faira kana zip folder kana code iri private kana local. Kana ichi indexed, chete kutanga kufona. Switch pakati loaded repos pasina kushaya kufona.

Vazhinji GitHub repositories basa nhasi kuburikidza URL, pamwe chete nedirect file/folder/zip kurodha pasi chero chinhu kwete pa GitHub. GitLab uye Bitbucket URL kutumira zviri pa roadmap. Kusvikira ipapo, kune GitLab kana Bitbucket chirongwa chete kurodha pasi repo se zip uye kurodha pasi — chitima kusangana kurodha pasi kodhi zvakafanana kune a cloned repo.

Yeah. It runs on our self-hosted Qwen 3 Coder model on the daily free token pool — 2,500 tokens/day anonymous, 10,000/day with a free account. A typical question-and-answer turn costs ~100-300 tokens. Indexing a repo is cheap; you only spend tokens when you actually ask questions. Premium models (Claude Sonnet / GPT-5) are available per-call for very large or tricky reasoning over the codebase.

Hapana kudzidziswa, chero nguva. Kukwira mafaera uye cloned repos inowanzochengetwa chete kwenguva yesession yako kuitira kuti AI ikwanise kubvunza mibvunzo, uyezve kubvisa. Public repos iwe unotarisa pane zviri pachena. Private code iwe unokwira haizove nenguva yekugoverwa, haizove nenguva yekudzidzisa mamodheru, uye inogadziriswa otomatiki. Full details at /privacy/.

Zvimwe faira kusvika 10MB uye zvinyorwa zveprojekti kusvika kwauri 100MB / mamirioni mashoma ezvinyorwa zvemutauro zvinoratidzwa zvakachengeteka. Mazhinji madiki emonorepos anotsigirwa nekuratidzwa kwemafaira akakosha pakutanga — AI inowana machunks akabatanidzwa nechikumbiro chako kupfuura kupfuudza zvese mutsara munzira imwe chete. Binary assets, node_modules, build artifacts, uye lockfiles zvinoratidzwa otomatiki kuitira kuti zvinyorwa zvigare zvichitarisa pane chaiyo chizvarwa.

Iyo inoisa index yese ye repositi, wozowanawo zvinokosha zvikuru zvechikumbiro chese (retrieve-augmented). Izvi zvinochengeta mhinduro dzakachengeteka mumafaira akakodzera pasina kusvibiswa kwechirongwa chekutaura. Kana iwe uchibvunza nezvechikumbiro kana faira, inotora iyo kodhi pamwe nevanoikumbira/vanoikumbira; kana iwe uchibvunza mibvunzo yechivakwa, inotora ongororo yechivakwa. Unogonawo kutumira @-mention kune nzira kuti uite kuti itariswe.

All the popular ones — Python, JavaScript/TypeScript, Java, C/C++, C#, Go, Rust, Ruby, PHP, Swift, Kotlin, plus config (YAML, JSON, TOML), SQL, shell, Dockerfiles, and framework conventions (Django, Flask, React, Vue, Spring, Rails, Express, and more).Nekuti ndiyo imwe Qwen 3 Coder engine yakati wandei /code/ generators, inozivikanwa nemazwi ekunze uye nechirongwa chekuisa, kwete chete syntax.

Yeah — bvunza kuti igadzirise bug, refactor a function, wedzera kudzora kwematambudziko, kana kumisikidza chimiro uye inodzokera kushandurwa kwekodzero neruzivo rweshanduko. Iyi ndeyekuverenga chete kune yako repo (haisi kumanikidza commits), saka unonyora iyo yakapihwa diff uye unoishandisa iwe pachako. Kuti uite kugadziriswa-ne-debug kutenderera shandisa /code/debug/, uye /code/refactor/ kune shanduko dzikuru.

Yeah. Point it at a module and ask for unit tests (pytest, Jest, JUnit, etc.) and it writes them against the real signatures it reads. Ask for a README, docstrings, or API docs and it generates them from the actual code. For one-shot versions outside a repo chat, /code/test/ and /code/documentation/ and /code/readme/ are the dedicated tools.

Plain / chat/ mashoko kubva general knowledge uye chero zvaunogona kuisa mu meseji. Chat with Repo grounds every answer in your actual indexed codebase — it cites real files, follows imports across modules, and stays consistent with your project conventions. Use / chat/ for general coding help; use this when the answer depends on understanding how your specific project is wired together.

Yeah — the underlying code chat is reachable via POST to /v1/chat/ on api.free.ai with Bearer auth using a developer API key. Send your repo context or file contents as part of the request and stream the answer back, OpenAI-compatible. Useful for building code-review bots or CI assistants. Python / Node / cURL snippets at /api/.