Synced from dibs. This page is pulled from hivecommons/dibs@main during the docs build. Edit the canonical source in the dibs repository.

Dibs

Dibs

License

A place to offer software ideas to projects and retain credit for them.

Your idea, your credit, their code.

The missing contributor layer for the AI-agent era.

Dibs is a two-sided marketplace that connects ideators — people who call dibs on ideas: great insight, but no time, tooling, or inclination to write code — with hive-managed repositories: projects that use Hive to run coding agents under maintainer-chosen rules.

  1. Ideators post ideas — public or private — in plain language / markdown.
  2. Repos opt in to receive ideas, declaring topics and appetite.
  3. A language model (LLM) matches ideas to repos that want them; both the idea contributor and the receiving project must accept the match.
  4. On mutual acceptance, Dibs hands the ideator a prefilled GitHub issue — they file it themselves, under their own GitHub account, so the issue is natively attributed to them (label ideated). The receiving project can then have its agents work on it under its own review rules. In this default flow Dibs is just the matchmaker: it never files the issue for you.

Ideators are first-class contributors

Open source has always had a quiet contributor class with no outlet: researchers, operators, designers, power users — people who know exactly what a project needs but will never open a pull request. Open source has also always known ideas are contributions — the all-contributors spec has a 💡 “ideas” emoji, and the academic CRediT taxonomy credits “Conceptualization” as a first-class role. Dibs makes that credit real, machine-readable, and public.

Creators get credit. Agents do the work. Projects take the bow.

Every implemented idea traces back to its ideator: the GitHub issue credits the idea’s author, the resulting work carries that provenance, and the public credit wall (/api/credits, “Credit wall” in the UI) lists every ideator with a settled idea: a GitHub issue URL has been recorded. This credits the proposal, not proof that its implementation shipped or its issue was closed. Settled ideas appear regardless of their visibility setting: settling a private idea makes its credit facts (author, title/TLDR, target, issue URL, and time) public, but not its body or private detail endpoint.

Try Dibs in your browser

No local installation or Go toolchain is needed. Open dibs.hivecommons.dev to browse the public surface; posting needs a Hive Hub sign-in and filing the issue needs a GitHub account.

  1. Sign in and describe your idea in plain language. Choose public or private deliberately; unsettled private ideas are not included in the public wall.
  2. Review suggested repositories and offer the idea to a suitable project. For Hive-managed targets, both sides accept before issue filing.
  3. Open the prefilled GitHub issue, review it, and file it yourself.
  4. Confirm the resulting issue URL in Dibs. This step is settlement: it records the handoff, not completion of the proposed work. Confirming also publishes the credit facts above, even for an idea marked private.

Non-Hive GitHub targets can skip the receiving-project acceptance step. For settlement and privacy details, see the consumer API. To submit from a coding agent instead, see MCP setup.

Maintainer and developer reference

The following sections cover running Dibs, its API, and local development, not prerequisites for using the hosted site.

Architecture

Single Go binary (cmd/dibs) serving both the JSON API and an embedded static UI, deployed at its own subdomain: dibs.hivecommons.dev. The base path is configurable (DIBS_BASE_PATH), so path-prefixed reverse-proxy deployments also work.

PackagePurpose
pkg/serverHTTP server, base-path routing, embedded UI
pkg/authAuth bridge — validates the hive hub session cookie against the hub
pkg/storeIdea model + JSON file store (atomic writes, no external DB), offer/settlement state machine
pkg/fsutilShared atomic JSON persistence helper (temp file + rename, mode 0600) used by the file stores
pkg/apiIdea CRUD + matching/offer/feed/decide/notification API (author-scoped, private ideas never leak)
pkg/registryHive-managed repo profiles + “accepting ideas” opt-in
pkg/matchLLM idea↔repo scoring via litellm gateway, cached TLDRs, ”✨ Embellish” draft refinement, deterministic keyword fallback
pkg/settleSettlement — prefilled GitHub new-issue URL the ideator files themselves (ideated label, 🐝 Dibs footer, URL-length budget) + issue-URL confirmation; legacy token mode. Ideas can target ANY GitHub repo: non-hive targets skip acceptance and their issues carry a “request a hive” growth CTA
pkg/notifyIn-app notification feed (bell): matches, offers, decisions, issues
pkg/mcpserverStreamable HTTP MCP endpoint exposing Dibs tools (see Submit ideas from your agent)
pkg/intakeExtracts idea text from uploaded documents or transcribed audio
pkg/gameGamification layer — points, levels, badges — recomputed from stored idea state, never a mutable counter
pkg/catalogBuilds and searches a separate CNCF project catalog
pkg/historyBackfills public GitHub activity for hive-managed repos; persists daily counts for repo index charts
pkg/indexformulaWeighted composite behind the repo market index
pkg/newsTurns recent merged PRs into repo news cards
pkg/depsSingle place declaring the subsystem dependencies the HTTP server, JSON API, and MCP endpoint are wired with

Configuration

Env varDefaultMeaning
DIBS_BASE_PATH/Base path every route/asset is served under (set e.g. /ideas for path-prefixed proxying)
DIBS_ADDR:8080Listen address
DIBS_METRICS_ADDR(unset)Internal Prometheus /metrics listener (e.g. :9090); unset keeps it off. See deploy/
HUB_URLhttps://hive.hivecommons.devHive hub for session validation & repo sync
DATA_DIR/dataJSON store directory
REPOS_SEED_FILE(unset)Static JSON seed of repo profiles for dev/demo
DIBS_LLM_BASE_URL(unset)OpenAI-compatible gateway (hive litellm), e.g. http://litellm:4000/v1. Unset → deterministic keyword matcher
DIBS_LLM_API_KEY(unset)Bearer token for the LLM gateway
DIBS_LLM_MODELgpt-4o-miniModel name routed by the gateway
DIBS_GITHUB_TOKEN(unset)Legacy mode only for issue creation: when set, Dibs opens the credited issue server-side on accept. Unset (default), the ideator files a prefilled GitHub issue themselves — native attribution. Also used, when present, to authenticate the GitHub lookup that verifies a confirmed issue URL (anonymous otherwise)
DIBS_ADMINS(unset)Comma-separated, case-insensitive GitHub logins granted admin access (idea-moderation endpoints)
DIBS_CLANKER_MARKERShive: agent=,hivecommons-hive[bot],hivecommons-hive[bot]Comma-separated, case-insensitive markers matched against PR branch/labels/body/author to classify agent activity
DIBS_INTAKE_MAX_MB25Max upload size (MB) accepted for idea-intake file uploads
DIBS_INTAKE_EXTRACT_WORKER(on)Set to off to extract uploaded documents in-process instead of in a memory-limited, time-limited child worker (not recommended: crafted documents can then exhaust the server’s memory)
DIBS_STT_URL(unset)Speech-to-text gateway URL; when set, enables voice/audio idea submission
DIBS_STT_KEY(unset)API key for the STT gateway
DIBS_STT_MODEL(unset)Model name routed by the STT gateway

Voice recording: the browser records at 32 kbps (audioBitsPerSecond) and uploads 10 s slices as it goes; the file name and type follow the recorder’s real container (webm, ogg or m4a). At 32 kbps the default 25 MB cap (DIBS_INTAKE_MAX_MB, which is also the STT request limit for OpenAI-style backends) holds roughly 100 minutes; 30 to 60 minutes is about 7 to 14 MB. A recording that outgrows the cap is refused. Audio is held in a temp file only until transcription and is never kept.

Legacy IDEATE_* names (the pre-rename prefix) are still honored as fallbacks for every DIBS_* variable.

Roadmap

See ROADMAP.md for what is planned next. Delivery history:

  • Wave 1 (done): scaffold, hub auth bridge, idea CRUD, repo registry.
  • Wave 2 (done): LLM matching + TLDRs, swipe UX (“offer” / “pass”), issue settlement (credited GitHub issues), notifications.
  • Wave 3 (done): deployment (GHCR image + deploy/ manifests for dibs.hivecommons.dev), public landing page, public credit wall, ideator profile stats.
  • Wave 4 (done): matchmaker settlement — the ideator files a prefilled GitHub issue themselves (native attribution, ideated label) and confirms the issue URL; LLM-assisted idea refinement on posting and repo-tailored expansion on submission; token-based settlement demoted to legacy.
  • Later: cookie-domain/hub-OAuth session sharing, non-hive receptor repos, idea economics.

Deployment

Every push to main publishes ghcr.io/hivecommons/dibs (latest + commit sha) via .github/workflows/docker.yml; the image is distroless and runs as non-root. Plain Kubernetes manifests for dibs.hivecommons.dev (Deployment, Service, cert-manager TLS Ingress, PVC, ConfigMap/Secret) live in deploy/, including the required DNS record and hub-cookie prerequisites.

Public surface (no sign-in required)

RoutePurpose
GET /Landing page (pitch + sign-in) — signed-in users get the full app
GET /api/creditsCredit wall data: settled ideas only (handle, title, TLDR, repo, issue URL)
GET /api/leaderboardAggregate ideator scores/levels/badges
GET /api/tickerPublic idea ticker tape for the logged-out landing page
GET /api/boardLive-markets board shown on the logged-out landing page
GET /api/statsAggregate, non-identifying counts
GET /api/repos/{org}/{repo}/indexRepo value-index chart series
GET /api/repos/{org}/{repo}/newsRepo news feed
GET /api/repos/{org}/{repo}/qr.pngRepo QR code
GET /healthzLiveness check + embedded git version
GET /readyzReadiness check — verifies the data store is accessible/writable

Everything else requires a hive hub session; signed-in ideators additionally get GET /api/me/stats (ideas posted / offered / accepted / settled).

For response schemas, eligibility/privacy rules, settlement actions, rewards, and stability levels, see the credit-wall consumer API.

Submit ideas from your agent

Dibs exposes a stateless Streamable HTTP MCP endpoint at https://dibs.hivecommons.dev/mcp, so Claude Code, Copilot CLI, Cursor, Gemini CLI, Codex, and other MCP clients can submit ideas without leaving the agent.

Dibs is listed in the official MCP Registry as dev.hivecommons/dibs (registry entry). Search for that full name: a plain dibs search also returns unrelated servers with the same name, including the 1stDibs marketplace and other coding-agent tools called dibs. How the listing is published is covered in MCP Registry publishing.

Available tools:

ToolAuthPurpose
submit_idea(title, description, tags?)RequiredCreates a private draft idea owned by you and returns its id and API URL
list_my_ideas()RequiredLists your ideas with lifecycle phase/status
get_idea(id)Optional for public ideas; required for private ideas (author, or owner of a repo holding a pending or accepted offer)Shows detail, matches, offers, and settlement state
list_repos()Not requiredLists registered repo venues

Token

Use Authorization: Bearer <token>. Dibs first asks the Hive Hub /api/saas/whoami endpoint to verify the bearer token server-to-server; the hub already accepts GitHub bearer tokens for registered hub users. If that is not practical, copy the raw hive_hub_user cookie value from your browser after signing in at https://hive.hivecommons.dev; Dibs falls back to verifying that value through the same hub whoami cookie flow used by the web UI.

In Chrome/Edge: open DevTools → Application → Cookies → https://hive.hivecommons.dev (or https://dibs.hivecommons.dev) → copy the hive_hub_user value.

Claude Code

claude mcp add --transport http dibs https://dibs.hivecommons.dev/mcp \
  --header "Authorization: Bearer <your-token-or-hive_hub_user-cookie-value>"

Claude Desktop and ChatGPT connectors

Both accept a remote MCP server over Streamable HTTP, so the same endpoint works without a local process.

Claude Desktop: Settings -> Connectors -> Add custom connector, with the URL https://dibs.hivecommons.dev/mcp. Where the connector UI allows a custom header, set Authorization: Bearer <token>; the read-only tools work without one, and submit_idea needs it.

ChatGPT: Settings -> Connectors -> Add custom connector (available on plans where custom MCP connectors are enabled), using the same URL and header.

GitHub Copilot CLI and VS Code

Copilot CLI has a one-line command to add a remote MCP server:

copilot mcp add --transport http \
  --header "Authorization: Bearer <your-token-or-hive_hub_user-cookie-value>" \
  dibs https://dibs.hivecommons.dev/mcp

This writes to ~/.copilot/mcp-config.json using the same mcpServers / type: "http" shape as the Generic MCP JSON block below.

VS Code reads ~/.copilot/mcp-config.json (shared with Copilot CLI) and workspace .mcp.json files. Both use the same mcpServers format. For more details, see the Copilot CLI documentation and VS Code MCP server documentation.

Cursor

Cursor reads MCP configuration from ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-level). Use the mcpServers format with url and headers:

{
  "mcpServers": {
    "dibs": {
      "url": "https://dibs.hivecommons.dev/mcp",
      "headers": {
        "Authorization": "Bearer ${env:DIBS_TOKEN}"
      }
    }
  }
}

Cursor supports ${env:NAME} interpolation in headers, so you can set DIBS_TOKEN as an environment variable rather than storing it in the file. For details, see the Cursor MCP documentation.

Gemini CLI

gemini mcp add --scope user --transport http \
  --header "Authorization: Bearer <your-token-or-hive_hub_user-cookie-value>" \
  dibs https://dibs.hivecommons.dev/mcp

This adds the server to ~/.gemini/settings.json; drop --scope user to add it to the project’s .gemini/settings.json instead. For details, see the Gemini CLI MCP documentation.

Codex

Codex (CLI and IDE extension) reads MCP servers from ~/.codex/config.toml. bearer_token_env_var keeps the token out of the file and sends it as Authorization: Bearer <token>:

[mcp_servers.dibs]
url = "https://dibs.hivecommons.dev/mcp"
bearer_token_env_var = "DIBS_TOKEN"

Then export DIBS_TOKEN=<your-token-or-hive_hub_user-cookie-value> before starting Codex. For details, see the Codex MCP documentation.

Generic MCP JSON

{
  "mcpServers": {
    "dibs": {
      "type": "http",
      "url": "https://dibs.hivecommons.dev/mcp",
      "headers": {
        "Authorization": "Bearer <your-token-or-hive_hub_user-cookie-value>"
      }
    }
  }
}

Recall ideas you never acted on

Dibs ships an MCP prompt, recall_ideas, for the ideas that never made it to a form: the ones mentioned in passing and forgotten. Dibs cannot find those itself - only the assistant holding your history can - so the prompt asks it to.

It instructs the assistant to search its memory and your past conversations for product ideas, feature wishes, requirements and specs you described but never acted on, report each with enough context to act on, and then ask which ones to list. It submits only what you pick.

ArgumentPurpose
scopeOptional focus - a project, a repo, a period like “the last year”. Omit to search everything available.
limitMaximum candidates to report. Defaults to 10, capped at 50.

In Claude Code and Claude Desktop the prompt appears as a slash command once the connector is added. Clients that do not surface prompts in their UI can still call prompts/get directly.

Capture voice notes from a Plaud recorder

dibs ingest plaud turns Plaud Note / Note Pro recordings into private draft ideas, unattended and at no cost beyond the Plaud subscription. It talks to the official, free Plaud MCP server (npx -y @plaud-ai/mcp@latest, over stdio), lists recordings since its cursor, fetches each one’s Plaud summary and transcript, and submits them with the submit_idea tool (tags plaud,voice-note).

The flow is: record on the Plaud → the Plaud app uploads and transcribes it → dibs ingest plaud (one pass, or a poller) → a private draft idea appears in Dibs, tagged plaud, with the Plaud summary and transcript as its body.

# Once: sign in to Plaud through its MCP server (the token stays in ~/.plaud).
# Then, with your hub token (see "Token" above):
export DIBS_TOKEN=...
dibs ingest plaud --dry-run          # first time: see what would be submitted
dibs ingest plaud                    # one pass, for cron/launchd
dibs ingest plaud --interval 15m     # or keep polling

First run: Plaud sign-in

The Plaud MCP server owns the Plaud login. On its first start it prints a sign-in URL on stderr (which dibs ingest plaud forwards) and waits for the browser to redirect to its callback on http://localhost:8199. Open the URL, approve, and the server writes its OAuth token to ~/.plaud/tokens-mcp.json; later runs are unattended. Dibs never reads, copies, or logs that file.

On a headless or remote host the callback still has to reach the machine running the server. Either forward the port while you sign in:

ssh -L 8199:localhost:8199 user@host   # then run dibs ingest plaud there and open the URL locally

or sign in once on your laptop (npx -y @plaud-ai/mcp@latest from any MCP client) and copy ~/.plaud/tokens-mcp.json to the host, keeping it readable only by that user. --home (or $DIBS_PLAUD_HOME) points the server at a different $HOME, so a service account can keep its token store under, say, /var/lib/dibs-plaud/.plaud/ without affecting the caller’s own ~/.plaud.

FlagDefaultPurpose
--server$DIBS_URL or https://dibs.hivecommons.devDibs base URL (including any base path)
--token$DIBS_TOKENHub bearer token; prefer the env var, flags show up in ps. Never logged
--interval0Poll interval; 0 runs once
--cursor~/.dibs/plaud-cursor.jsonSubmitted Plaud ids, newest recording time, recent submission times
--mcp-command$DIBS_PLAUD_MCP_COMMAND or npx -y @plaud-ai/mcp@latestPlaud MCP server command (whitespace-separated, no shell quoting)
--since-days7How far back the first run looks
--tagsplaud,voice-noteComma-separated tags
--max-per-hour / --max-per-day10 / 30Submission budget per rolling hour / 24h (0 = unlimited)
--max0Recordings handled per run (0 = no cap); the rest wait for the next run
--dry-runoffLog each idea that would be submitted; submit nothing and leave the cursor untouched
--home$DIBS_PLAUD_HOME or inherit$HOME for the Plaud MCP server, i.e. the parent of its .plaud/ token store

Each recording is submitted once: its Plaud id is recorded in the cursor file right after the submission succeeds. Recordings with no summary or transcript yet are retried on the next run. Long transcripts are fetched page by page (following the server’s next_cursor). When the budget is used up the run logs budget_exhausted=true; when Dibs answers HTTP 429 it logs rate_limited=true; either way the run stops and the remaining recordings wait for the next run. Descriptions are cut to the 64 KiB idea body limit. The helper never reads or copies Plaud’s OAuth token (~/.plaud/tokens-mcp.json).

The Plaud MCP server is third-party code that npx fetches from the registry on every start, so it is started with an allowlisted environment rather than the caller’s: PATH, HOME (or --home), USER/LOGNAME, SHELL, TMPDIR, TZ, TERM, locale (LANG, LC_*), XDG_*, NODE_* and npm_config_* settings, proxy and CA variables (HTTP(S)_PROXY, NO_PROXY, SSL_CERT_FILE/SSL_CERT_DIR), PLAUD_*, DIBS_PLAUD_*, and the Windows basics. Anything else — DIBS_TOKEN, GITHUB_TOKEN, cloud or model-provider keys — never reaches it, and a name containing TOKEN, SECRET, PASSWORD, CREDENTIAL or AUTH is dropped even inside those prefixes (so NODE_AUTH_TOKEN is not forwarded). To stop @latest from pulling an unreviewed upstream release on each poll, pin it: --mcp-command "npx -y @plaud-ai/mcp@<version>" (or $DIBS_PLAUD_MCP_COMMAND).

Future recording timestamps are clamped to the submission time in the cursor, so they do not move the next listing window into the future. Existing cursors already set in the future need their newest field corrected manually; retain the seen entries to avoid resubmitting recordings.

Privacy

Recordings leave the device only through Plaud’s own app and cloud; this helper reads them back through Plaud’s API with your Plaud login and sends the summary and transcript text to Dibs as a private draft owned by your hub identity. Nothing is published until you promote the draft. Audio is never fetched. If you would rather not run an unattended poller, export the transcript or summary from the Plaud app (TXT/Markdown) and upload it yourself with POST /api/intake (multipart field file, same hub token, 25 MB cap, 10/h and 30/24h per identity); the same idea-shaping pipeline turns it into a draft.

Cron (every 15 minutes):

*/15 * * * * DIBS_TOKEN=... /usr/local/bin/dibs ingest plaud >>"$HOME/.dibs/plaud.log" 2>&1

launchd (~/Library/LaunchAgents/dev.hivecommons.dibs-plaud.plist, load with launchctl load on that file):

 
 
<plist version="1.0"><dict>
  <key>Label</key><string>dev.hivecommons.dibs-plaud</string>
  <key>ProgramArguments</key><array>
    <string>/usr/local/bin/dibs</string><string>ingest</string><string>plaud</string>
  </array>
  <key>EnvironmentVariables</key><dict>
    <key>DIBS_TOKEN</key><string>...</string>
    <key>PATH</key><string>/usr/local/bin:/opt/homebrew/bin:/usr/bin:/bin</string>
  </dict>
  <key>StartInterval</key><integer>900</integer>
</dict></plist>

Capture ideas dictated with Wispr Flow

No setup needed for the common case. Wispr Flow types into whatever field has focus, so dictating straight into the idea form at dibs.hivecommons.dev, or into an agent prompt that calls the Dibs MCP submit_idea tool, already works. The poller below is for ideas you dictate elsewhere (Notes, Slack, an editor) and want collected later.

dibs ingest wisprflow reads Wispr Flow’s local dictation history and submits the dictations meant as ideas as private draft ideas (tags wisprflow,voice-note). Wispr Flow has no dictation-history API, so it reads the desktop app’s SQLite file read-only through the sqlite3 CLI (ships with macOS): ~/Library/Application Support/Wispr Flow/flow.sqlite on macOS, %APPDATA%\Wispr Flow\flow.sqlite on Windows. --db may instead point at a copy of that file or at an export folder of .json, .ndjson/.jsonl, .csv or .md files (one dictation per markdown file).

Most dictations are not ideas, so only these are imported:

  • dictations that start with a trigger phrase, by default dibs idea or idea for dibs (case and punctuation do not matter: “Dibs idea: …”, “Idea for Dibs — …”); the phrase is stripped from the idea;
  • and/or, with --apps, dictations made in an allowed app (bundle id or name, e.g. --apps com.apple.Notes or --apps Notes); --trigger "" with --apps imports every dictation made in those apps;
  • with at least --min-words words after the trigger.

The idea title is the first ten words after the trigger; the description is the full dictation (your edit if you made one, otherwise Flow’s formatted text) with a footer giving the dictation time and the app.

export DIBS_TOKEN=...                   # hub bearer token
dibs ingest wisprflow --dry-run         # first time: see what would be submitted
dibs ingest wisprflow                   # one pass, for cron/launchd
dibs ingest wisprflow --interval 15m    # or keep polling
FlagDefaultPurpose
--db$DIBS_WISPRFLOW_DB or the per-OS path above (none on Linux)flow.sqlite, a copy of it, or an export folder
--triggerdibs idea,idea for dibsComma-separated phrases a dictation must start with; empty requires none (then --apps is required)
--appsallComma-separated app allow-list (bundle id substring or app name)
--min-words5Minimum words after the trigger
--sqlite3sqlite3sqlite3 command used to read flow.sqlite
--server, --token, --interval, --since-days, --max-per-hour / --max-per-day, --max, --dry-runas for dibs ingest plaudShared with dibs ingest plaud
--cursor~/.dibs/wisprflow-cursor.jsonSubmitted transcript ids, newest dictation read, recent submission times
--tagswisprflow,voice-noteComma-separated tags

Each dictation is submitted once (dedupe on Wispr Flow’s transcriptEntityId). The cursor follows the newest finalised dictation read, idea or not, and each run re-reads two hours behind it, because Flow updates a row in place when it finishes formatting. Archived dictations and the audio/screenshot columns are never read. Run it where Wispr Flow runs (your Mac or PC), from cron or launchd as for Plaud with wisprflow in place of plaud; on macOS the process reading flow.sqlite may need Full Disk Access. The table schema is community-documented and may change with a Wispr Flow release; the export-folder path is the fallback.

Operations and further reading

Development

Requires Git and Go 1.27 or newer. Clone https://github.com/hivecommons/dibs.git, then run these commands from the checkout’s top-level dibs folder. For authenticated local use, follow Running locally with sign-in; fakehub is for development only, not a production authentication service.

go test -race -count=1 ./...
go run ./cmd/dibs            # serves on :8080 at /
go build -o dibs ./cmd/dibs  # builds the binary (plain `go build ./...` writes none)
./dibs --version             # prints the embedded commit

Running locally with sign-in

Every route except the public surface needs a hive hub session. For local work, hack/fakehub is a dev-only stand-in for the hub: it accepts any non-empty hive_hub_user cookie as that user and serves a small static repo list. Run it in one terminal, then point Dibs at it in another:

go run ./hack/fakehub        # listens on :9999 (override with FAKEHUB_ADDR)
HUB_URL=http://127.0.0.1:9999 DATA_DIR=./data go run ./cmd/dibs
curl -H 'Cookie: hive_hub_user=dev' http://127.0.0.1:8080/api/me

To load richer repo profiles than fakehub’s two entries, also set REPOS_SEED_FILE=hack/seed-repos.example.json.

Smoke-testing the container image

docker build only proves the image compiles. hack/smoke.sh runs it the way deploy/deployment.yaml does (uid 65532, read-only root filesystem, only /data writable, all capabilities dropped) and checks --version is stamped, /healthz and /readyz answer 200, the landing page serves with HUB_URL substituted and the security headers set, the auth wall answers 401/502 around the public API, /metrics exposes the dibs_* series the alerts query (labelled by the route groups just exercised), and SIGTERM drains to exit 0:

docker build --build-arg GIT_HASH="$(git rev-parse HEAD)" -t dibs:smoke .
hack/smoke.sh dibs:smoke "$(git rev-parse HEAD)"

Contributing & Community

Dibs is part of Hive Commons, a family of tools for working with AI agents.

License

Apache-2.0 — see LICENSE.

Handshake icon: Twemoji, CC-BY 4.0.