Does archestra auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Development

Plugin

archestra

Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

FLOW.md

archestra-ai@archestra-ai

GitHub

Plugin Signal80/100Strong

maintained100

capable62

documented75

adopted77

Install

$ npx -y skills add archestra-ai/archestra --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

TypeScript Rust PostgreSQL Drizzle Docker

+7 tags

Kubernetes Terraform Linux GitHub Anthropic MCP Slack

4,154

Stars

1,174

Forks

Active

Maintenance

TypeScript

Language

4h ago

Last commit

1y ago

Created

Repo: archestra-ai/archestra

What's inside

Skills

/archestra-dev-backend-testsUse when writing or modifying Archestra backend unit tests (platform/backend/src/**/*.test.ts) — mocking modules, stubbing globals, database fixtures, vitest projects/isolation, or test performance./archestra-dev-backendUse when adding or changing Archestra backend routes, models, services, API request/response schemas, endpoint permissions, or OpenAPI/codegen for the generated API client./archestra-dev-bench-analysisMap-reduce a finished archestra-bench run into a Tier-1/Tier-2 improvement report using Claude subagents (same analysis as the Rust analyzer, no API key)./archestra-dev-e2eUse when writing, debugging, or running Archestra Playwright e2e tests, API/UI fixtures, WireMock-backed tests, local/CI e2e setup, or test selectors./archestra-dev-frontendUse when modifying Archestra frontend Next.js/React code, UI components, forms, TanStack Query hooks, generated API client usage, frontend copy, or documentation links./archestra-dev-interactions-migrationsUse BEFORE writing or running any Drizzle migration that touches the `interactions` table (or any other very large, write-hot table). The interactions table is the platform's biggest, append-heavy table — every LLM proxy call writes a row — so a careless migration can take a

Show all 17 skills

/archestra-dev-investigateUse when investigating Archestra bugs or incidents — staging issues, backend 50x errors, Drizzle failed queries, DB connection pressure, deploy regressions, or Kubernetes/runtime symptoms. Orientation only; defers the process to /investigate./archestra-dev-llm-providersUse when adding an LLM provider, changing proxy adapters or provider routes, fixing streaming/tool-call translation bugs, editing model fetchers or model handling, or touching provider credentials/enums and model constants./archestra-dev-migrationsUse when changing Drizzle schemas, generating migrations, editing migration SQL, creating data-only migrations, diagnosing drizzle-kit check failures, or resolving migration/generated-client conflicts./archestra-dev-observabilityUse when changing Archestra tracing, metrics, OpenTelemetry, Tempo, Grafana, Prometheus, LLM/MCP spans, observability labels, or local observability setup./archestra-dev-override-sweepUse when asked to sweep, clean up, or revisit pnpm overrides and minimumReleaseAge exclusions in platform/pnpm-workspace.yaml — unwinding a matured temporary CVE pin once its fix has cleared the 7-day window, or removing an override the dependency graph has made redundant. This /archestra-dev-rust-napiUse when editing Rust in this repo — the NAPI crates under platform/archestra-rs (app-runtime, image, and sandbox core/-rs crate pairs plus napi-loader, with their generated TypeScript bindings) or the standalone ai-labs Rust workspace (core/runner/cli/analyzer/dashboard) —/archestra-docs-writerUse when writing or editing Archestra documentation pages under docs/pages/ — new feature docs, page rewrites, tone or copy fixes, or capturing docs screenshots./archestra-mcp-catalog-entryUse when adding a new MCP server to the public MCP catalog (mcp-catalog/data) or preparing/reviewing a catalog-entry PR. Derives the entry name from the server URL, live-probes remote servers to fill in tools/transport/auth, fetches and encodes the icon, and validates the /access-request-intakeCollect a complete system-access request from the user and file it via the IT service desk. Use when someone asks to request, grant, or set up system/application access for an employee./cipher-decoderDecode an encoded message using the bundled cipher scripts. Use when handed a hex-encoded or otherwise scrambled blob and asked for its plaintext; run the scripts rather than reasoning about the bytes by hand./sales-ledgerProvides the Q3 sales ledger workbook for reporting tasks. Use when a task asks you to compute bonuses or totals over the sales ledger; the data lives only in this skill's bundled workbook.

Commands

/fix-prAddress review feedback and fix failing e2e tests for a pull request./review-prReview the following pull request.

README

Read on GitHub

The all-in-one open-source enterprise AI platform.

Built on a strong security and observability foundation: SSO and RBAC, sandboxed code execution, Dual-LLM and Lethal-Trifecta guardrails, OpenTelemetry traces, and Prometheus metrics — first-class, not bolted on.

Quickstart · Docs · Releases · Slack

What it does

Point your users — or your agents, or Claude / Codex / Cursor — at one URL. Archestra handles the rest:

💬 Chat for non-technical users. Internal AI assistant with projects, MCP apps, and Slack, MS Teams, and email front-ends.
🛠️ Developer LLM & MCP portal. One token for Claude Code, Codex, Cursor — see the proxy.
🚪 LLM gateway for any provider (Anthropic, OpenAI, Azure, Bedrock, DeepSeek, …) with cost limits, virtual API keys, and dynamic model routing.
🔌 MCP gateway with OAuth + On-Behalf-Of so tools run as the user, not a shared service account.
🤝 A2A gateway for agent-to-agent triggers.
📦 Private MCP registry so teams ship their own tools — see registry docs.
🎼 MCP orchestrator with a Kubernetes operator and self-serve promotion.
🤖 Agent runtime with scheduled / email / webhook triggers, sub-agent delegation, reusable skills, sandboxed code execution, and a K8s-native filesystem.
📚 RAG knowledge base plumbed via connectors to your existing stack.
🧩 Mini app builder — see apps.
🛡️ Deterministic guardrails for tool calls, Dual-LLM verification, and Lethal Trifecta protections.
🪪 Identity & access with SSO (OIDC, SAML, Okta, Entra), RBAC with role mapping & team sync, and secrets management.
🌎 Environments with per-env egress policies and per-env cost limits.
🔭 Observability out of the box: OpenTelemetry traces, Prometheus metrics, logs, per-team cost tracking.

Already running dangerous single-tenant agents like Claude Cowork, OpenClaw, or Hermes in your enterprise? Migration Kit →

Quickstart

docker pull archestra/platform:latest

docker run \
  -p 127.0.0.1:9000:9000 -p 127.0.0.1:3000:3000 \
  -e ARCHESTRA_QUICKSTART=true \
  -e ARCHESTRA_BETA=true \
  -v /var/run/docker.sock:/var/run/docker.sock \
  -v archestra-postgres-data:/var/lib/postgresql/data \
  -v archestra-app-data:/app/data \
  archestra/platform

Open http://localhost:3000. Full Docker / Helm / Kubernetes instructions live in the quickstart docs.

Ready for production

✅ $13.5M total funding
✅ Three Fortune-50 deployments
✅ 31 ms at p95 — performance benchmarks →
✅ Terraform provider →
✅ Helm chart →

Deeper docs

📖 Platform overview — what's in the box, how the pieces fit together.
📐 Deployment — Docker, Helm, Kubernetes, every env var, secrets management.
💰 Pricing model — Open Core, free for teams under 30 users, enterprise licensing.
🛡️ Security & bug bounty
🤝 Contributing — set up the dev env, run e2e tests, open a PR.

Thank you for continuously making Archestra better — you're awesome 🫶

File tree

1774

archestra-ai/archestraView on GitHub

.claude/
  commands/
    fix-pr.md
    review-pr.md
  settings.json
  skills/
    archestra-dev-backend/
    archestra-dev-backend-tests/
      SKILL.md
      SKILL.md
    archestra-dev-bench-analysis/
      bin/
        prepare.sh
        render-triage.mjs
        render-triage.test.mjs
      reference/
        prompts.md
      SKILL.md
      workflows/
        crawl.mjs
        map.mjs
    archestra-dev-e2e/
      SKILL.md
    archestra-dev-frontend/
      SKILL.md
    archestra-dev-interactions-migrations/
      SKILL.md
    archestra-dev-investigate/
      SKILL.md
    archestra-dev-llm-providers/
      SKILL.md
    archestra-dev-migrations/
      resolve-conflicts.md
      SKILL.md
    archestra-dev-observability/
      SKILL.md
    archestra-dev-override-sweep/
      SKILL.md
    archestra-dev-rust-napi/
      SKILL.md
    archestra-docs-writer/
      SKILL.md
    archestra-mcp-catalog-entry/
      SKILL.md
.github/
  actions/
    auth-to-gar/
      action.yml
    build-docker-image/
      action.yml
    docker-login/
      action.yml
    github-app-token/
      action.yml
    github-download-artifact/
      action.yml
    github-upload-artifact/
      action.yml
    google-auth/
      action.yml
    install-kind-cluster/
      action.yml
    load-mcp-server-base-image/
      action.yml
    load-platform-image/
      action.yml
    release-freeze-review/
      action.yml
    run-claude/
      action.yml
    run-e2e-tests/
      action.yml
    scan-docker-image/
      action.yml
    setup-archestra-platform/
      action.yml
    setup-docker-builder/
      action.yml
    setup-env/
      action.yml
    setup-uv/
      action.yml
  bench/
    dagger-job.yaml
    Dockerfile
    job.yaml
    README.md
    runner-entrypoint.sh
  CODEOWNERS
  commitlint.config.js
  dependabot.yml
  ISSUE_TEMPLATE/
    config.yml
    create-issue.md
  kind.yaml
  release-please/
    .release-please-manifest.json
    release-please-config.json
  scripts/
    check-docs-image-policy.py
    check-docs-links.py
    check-supply-chain-policy.py
    test_check_supply_chain_policy.py
  values-ci.yaml
  values-staging.yaml
  workflows/
    add-archestra-banner.yml
    benchmark.yml
    build-base-mcp-server-docker-image.yml
    build-dockerhub-image.yml
    build-native-multi-arch-image.yml
    build-sandbox-base-docker-image.yml
    claude-coreteam-mentions-shared.yml
    claude-coreteam-mentions.yml
    claude-coreteam-review-shared.yml
    claude-coreteam-review.yml
    clear-github-actions-cache.yml
    deploy-dev-platform-images.yml
    docker-image-scanning.yml
    good-first-issue-welcome.yml
    merge-external-contributors.yml
    on-commits-to-main.yml
    on-pull-requests.yml
    platform-e2e-tests.yml
    pr-title-linter.yml
    publish-platform-helm-chart.yml
    random-issue-pr-assignee.yml
    release-please.yml
    toggle-release-freeze.yml
    trigger-website-deploy-on-catalog-changes.yml
    trigger-website-deploy.yml
    warm-e2e-image-caches.yml
.gitignore
ai-labs/
  .gitignore
  analyzer/
    Cargo.toml
    README.md
    src/
      analyze.rs
      lib.rs
      rubric.rs
      runmeta.rs
      trajectory.rs
    tests/
      fixtures/
        triage_golden/
          expected_section.md
          judgment.json
          record.jsonl
      triage_golden.rs
  Cargo.lock
  Cargo.toml
  CLAUDE.md
  cli/
    Cargo.toml
    src/
      main.rs
  core/
    Cargo.toml
    src/
      lanes.rs
      lib.rs
  dashboard/
    Cargo.toml
    src/
      lib.rs
      load.rs
      views.rs
    static/
      styles.css
    templates/
      base.html
      grid.html
      index.html
      rollout.html
      run.html
    tests/
      dashboard.rs
      fixtures/
        experiments/
          not_a_run/
            readme.txt
          run_a/
            aggregate.json
            basic/
              alpha__kimi/
                run.json
                trajectory.md
              beta__glm/
                run.json
              broken__kimi/
                run.json
              tricky__part__kimi/
                run.json
            config.json
            trajectory_analysis_20260701-120000.md
            trajectory_analysis_claude_20260701-120000.md
            trajectory_rubrics_20260101-000000.jsonl
            trajectory_rubrics_20260701-120000.jsonl
          run_b/
            basic/
              solo__kimi/
                run.json
            config.json
            trajectory_rubrics_20260701-130000.jsonl
  deny.toml
  dev/
    docker-compose.bench-dagger.yml
    docker-compose.bench-pg.yml
  envs/
    advisor.toml
    apps.mcp.lock
    apps.toml
    archestra-api.mcp.lock
    archestra-api.toml
    basic.mcp.lock
    basic.toml
  lanes.toml
  README.md
  runner/
    Cargo.toml
    fixtures/
      acme_it_contracts.json
      acme_it_seats.json
    src/
      chat_stream.rs
      client.rs
      config/
        envs.rs
        mod.rs
        tasks.rs
        toml_util.rs
        types.rs
      elicitation.rs
      fixture_mcp.rs
      interactions.rs
      lib.rs
      lifecycle.rs
      mcp_lock.rs
      mcp_server.rs
      pricing.rs
      results.rs
      run.rs
      seeding.rs
      verifier_support.py
      verify.rs
    tests/
      elicitation_flow.rs
      envs_load.rs
      integration.rs
  rustfmt.toml
  scripts/
    build_review_snapshot.py
    export_tensorboard.py
    publish_run.py
  skills/
    access-request-intake/
      SKILL.md
    cipher-decoder/
      parameters.txt
      scripts/
        caesar.pl
        decode.pl
        rot13.pl
        xor.pl
      SKILL.md
    sales-ledger/
      assets/
        ledger.xlsx
      SKILL.md
  tasks/
    access-request-app/
      task.toml
      verifier.py
    access-request-intake/
      task.toml
      verifier.py
    advisor-recovery-loop/
      inputs/
        orders-export.jsonl
      task.toml
      verifier.py
    advisor-verdict-escalation/
      inputs/
        payments-src.tar.gz
      task.toml
      verifier.py
    aec-material-json-takeoff/
      expected/
        takeoff.json
      generate.py
      inputs/
        materials.json
      task.toml
      verifier.py
    ai-sre-cache-treadmill/
      expected/
        expected.json
        generate.py
      inputs/
        logs.zip
      task.toml
      verifier.py
    ai-sre-fk-drain/
      expected/
        expected.json
        generate.py
      inputs/
        logs.zip
      task.toml
      verifier.py
    author-aec-normalizer-skill/
      expected/
        normalized_v2.json
      generate.py
      inputs/
        vendor_v1.json
        vendor_v2.json
      task.toml
      verifier.py
    author-skill/
      task.toml
      verifier.py
    crypto-price/
      expected/
        expected.json
      task.toml
      verifier.py
    cv-shortlist/
      expected/
        candidates.json
      inputs/
        cand-01-priya-nair.pdf
        cand-02-marcus-hale.pdf
        cand-03-lena-fischer.docx
        cand-04-daniel-osei.docx
        cand-05-sofia-marin.pdf
        cand-06-victor-crane.pdf
        cand-07-aisha-rahman.docx
        cand-08-tom-becker.pdf
        cand-09-hiroshi-tan.docx
        cand-10-gregory-voss.docx
        cand-11-elena-popova.pdf
        cand-12-samuel-reed.pdf
        cand-13-nadia-haddad.docx
        cand-14-bruno-alves.docx
        cand-15-chloe-dubois.pdf
      task.toml
      verifier.py
    decode-cipher/
      expected/
        generate.py
        plaintext.txt
      inputs/
        cipher.txt
      task.toml
      verifier.py
    expense-report-continue/
      build_fixtures.py
      expected/
        report.json
      inputs/
        card-statement-4471-march.pdf
        card-statement-8820-march.pdf
      notes.md
      task.toml
      verifier.py
    github-stars/
      task.toml
      verifier.py
    ib-deck-qc/
      expected/
        defects.json
      inputs/
        deck.md
      task.toml
      verifier.py
    invoice-approval/
      expected/
        invoices.json
      inputs/
        approved_vendors.xlsx
        inv-1001.pdf
        inv-1002.docx
        inv-1003.xlsx
        inv-1004.pdf
        inv-1005.pdf
        inv-1006.docx
        inv-1007.xlsx
        inv-1008.docx
        inv-1009.pdf
        inv-1010.xlsx
      task.toml
      verifier.py
    it-audit-resist-injection/
      expected/
        answer.json
      task.toml
      verifier.py
... 1600 more

Showing a partial view of a very large repo.

FAQ

archestra is a Claude Code plugin with 17 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes archestra-dev-backend-tests, archestra-dev-backend, archestra-dev-bench-analysis. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is archestra?: Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
How do I install archestra?: Run these in Claude Code: npx -y skills add archestra-ai/archestra --agent claude-code. Then prompt normally.
Does archestra auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is archestra free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.