/products

Pick the surface that fits where you are.

Clampd ships as a suite. Each surface targets a different audience: app developers wrap a client; AI coding tool users install a hook; security teams operate a dashboard; ops uses a CLI. All share the same gateway and the same 263 detection rules underneath.

★ Quickstart bundle

The starter bundle: SDK + dashboard + hosted gateway, in one signup.

If you want a turnkey on-ramp instead of picking individual products: sign in to app.clampd.dev, install the Python or TypeScript SDK with one line, get a free agent slot, and you're guarded. No infra to run, no Redis or Postgres to configure. Free under 25 agents and 500k tool calls/month. Upgrade only when you need OIDC SSO, compliance reports, or higher volume.

# 1. Sign in to get an agent + secret # 2. Install pip install clampd # or npm install @clampd/sdk # 3. Wrap your client client = clampd.openai( OpenAI(), agent_id="my-agent", ) # Done.
Individual products

clampd-actions PLANNED

CI/CD · DevOps

GitHub Action / GitLab CI runner that fires the 556-payload regression corpus against your agent code on every PR. Snyk-shaped product for AI agent security testing in CI. Coming after the launch wave.

Status: Planned for v0.18+
Targets: GitHub Actions, GitLab CI, CircleCI

clampd-replay PLANNED

Forensics · Compliance · Post-incident review

Pick any historical agent decision; reconstruct the full call: tool descriptors, params, matched rules, session-pattern flags, scope token issued, LLM-as-Judge verdict (if fired), final policy decision, downstream response. Forensic-grade replay built on the existing ClickHouse audit trail. Differentiator: no benchmarked competitor offers this.

Status: Concept; backed by existing audit data
Audience: Regulated industries, post-breach reviews

clampd-reports PLANNED · PREMIUM

GRC · Compliance · Governance teams

Maintained compliance evidence: HIPAA, GDPR, SOC 2, PCI-DSS templates kept current as the regulations evolve. Scheduled monthly/quarterly delivery. Activity inventory: agents observed, tool descriptors observed, MCP endpoints with traffic, policy violations grouped by agent/time/category. Source-available under BSL-1.1. The raw audit data lives in your own ClickHouse on every tier and is queryable directly. clampd-reports is the maintained alternative for teams who don't want to keep their templates current as compliance frameworks evolve.

You always own the data. Free tier: raw queryable audit trail in your storage.
Enterprise: maintained templates, scheduled delivery, exportable PDF/CSV, signed evidence packets.

clampd-replay PLANNED · PREMIUM

Forensics · Insurance · Regulators

When an alert fires (kill, repeated denials, behavioural anomaly), Clampd auto-assembles every related decision, agent activity, scope grant, and delegation hop into a single timestamped, signed incident packet. Ready for legal hand-off, insurance claims, or regulator review — without rebuilding the timeline by hand. Multi-cluster federation across distributed deployments. Long-term retention beyond dashboard defaults. Source-available under BSL-1.1. The underlying ClickHouse audit data is yours on every tier; clampd-replay is the templated workflow plus chain-of-custody signing infrastructure on top.

You always own the data. Free tier: raw audit data + manual reconstruction.
Enterprise: auto-packet generation, signed chain-of-custody, federation, long-term retention.

Deployment modes

The gateway behind every product runs in your environment of choice. Same code, same feature parity. Pick the operational fit:

Hosted SaaS · app.clampd.dev (zero infra) Docker Compose · 5 compose files (single, proxy, control, deploy, full) Kubernetes · Helm charts (planned) Air-gapped · on-prem, no telemetry Single binary · single-process gateway for low-volume / dev

See the setup page for the deployment-mode-specific install steps.