Enterprise AI agent orchestration. Manage, monitor, and scale your AI workforce.
One binary. Deploys in seconds. Control from Slack or CLI.
curl -fsSL https://klaw.sh/install.sh | shTrusted by teams at
Everything you need to run AI agents in production. From visibility to isolation to scheduling.
Familiar commands: get, describe, logs, apply. If you know kubectl, you know klaw.
@klaw status, @klaw run agent, @klaw logs. Manage agents from where you work.
One ~20MB binary. No Python, no Docker, no dependencies. Just download and run.
klaw get agents, klaw logs, klaw describe. Always know what your agents are doing.
Claude, GPT-4, Gemini, Llama via each::labs Router or direct provider access.
Logical isolation for teams and secrets. Use Podman containers for filesystem sandboxing.
klaw cron create — schedule agents to run hourly, daily, weekly. No external scheduler.
Controller-node architecture. Scale from laptop to enterprise cluster.
Slack, CLI, TUI, REST API. Deploy agents where your team works.
From Slack or CLI, tell klaw what you need. It connects to your tools, runs agents, and delivers results where you work.
Automatically analyze and score leads from your CRM
@klaw analyze my new leads from hubspot and score them based on engagement
📊 Analyzed 47 new leads from HubSpot: 🔥 **Hot (8 leads):** High engagement, visited pricing 3+ times ⚡ **Warm (23 leads):** Opened emails, downloaded resources ❄️ **Cold (16 leads):** Single touchpoint only Top priority: **Acme Corp** - CEO visited pricing page 5x this week. Recommend immediate outreach.
Get automated reports delivered to Slack on schedule
@klaw send me a daily revenue report every morning at 9am from Stripe
✅ Scheduled! I'll send your Stripe revenue report daily at 9:00 AM. **Report includes:** • Daily MRR & ARR • New subscriptions • Churned customers • Top transactions First report arrives tomorrow. Use `@klaw cron list` to manage schedules.
Monitor competitors and get alerts on changes
@klaw watch competitor pricing pages and alert me on changes
👁️ Now monitoring 5 competitor pricing pages: • competitor-a.com/pricing • competitor-b.com/plans • competitor-c.io/pricing I'll check every 6 hours and alert you immediately on: • Price changes • New tiers added • Feature updates • Positioning changes Last scan: all pages indexed. Ready to detect changes.
Auto-categorize and draft responses for support tickets
@klaw triage zendesk tickets and draft responses for common issues
🎫 Triaged 34 overnight tickets: **Auto-resolved (12):** Password resets, FAQ questions **Drafted responses (15):** Billing inquiries, feature questions **Escalated (7):** Complex bugs, enterprise requests 📝 15 draft responses ready for review in #support-drafts Avg response time improved: **4.2 hrs → 23 min**
Get intelligent summaries of pull requests and changes
@klaw summarize open PRs in the backend repo and flag any security concerns
🔍 Scanned 8 open PRs in `backend`: ⚠️ **PR #423** - SQL query uses string interpolation (potential injection) ✅ **PR #421** - Clean refactor, good test coverage ✅ **PR #419** - New endpoint, follows patterns 📝 **PR #418** - Large PR (847 lines), suggest splitting Recommend prioritizing security review on #423.
Analyze content metrics and get optimization suggestions
@klaw analyze our blog performance this month and suggest improvements
📈 Blog Performance Report (Feb 2024): **Top performer:** "AI in Production" - 12.4K views, 8.2% CTR **Underperforming:** "Getting Started Guide" - high bounce (78%) **Suggestions:** • Add video to Getting Started (competitors avg 3min video) • "AI in Production" readers also search for "scaling" - write sequel • Best posting time: Tuesday 10AM (2.3x engagement)
These are just examples. klaw can be configured for any workflow.
Inspired by Kubernetes, klaw brings familiar multi-tenancy patterns to AI agent orchestration. Isolate teams, projects, and environments with first-class namespace support.
Each team gets their own namespace with isolated agents, secrets, and resources. No cross-contamination.
$ klaw create namespace team-backend$ klaw create namespace team-frontend$ klaw create namespace team-data
Run dev, staging, and production environments on the same cluster with complete isolation.
$ klaw create namespace dev$ klaw create namespace staging$ klaw create namespace prod$# Deploy to specific environment$ klaw dispatch -n prod "analyze logs"
Set limits per namespace to control costs and prevent runaway agents from consuming all resources.
# Coming soon$ klaw set quota team-ml --max-tokens 1M/day$ klaw set quota team-ml --max-agents 10
Fine-grained access control. Users can only access namespaces they are authorized for.
# Switch namespace context$ klaw config set-context --namespace=team-backend$# List agents in current namespace$ klaw get agents
klaw borrows the best ideas from Kubernetes—namespaces, declarative configs, kubectl-style CLI—but is purpose-built for AI agents. No container orchestration overhead.
| Feature | klaw | Kubernetes |
|---|---|---|
| Installation | Single binary (~20MB) | Complex multi-component setup |
| Learning Curve | Minutes to get started | Weeks/months to master |
| Resource Usage | ~50MB RAM idle | 2GB+ for control plane |
| Namespaces | Built-in multi-tenancy | Built-in multi-tenancy |
| CLI Experience | kubectl-inspired, familiar | kubectl (the original) |
| Declarative Config | YAML manifests | YAML manifests |
| Focus | AI Agents & LLMs | Container orchestration |
| Built-in LLM Support | 300+ models ready | Requires custom setup |
Why not just use Kubernetes? Kubernetes is amazing for container orchestration, but it is overkill for AI agents. klaw gives you the patterns you love—namespaces, declarative YAML, familiar CLI—without the complexity of running a full K8s cluster. Think of it as "Kubernetes for AI Agents."
Familiar commands. Full visibility. Control from CLI or Slack.
From local development to enterprise clusters. Same commands, same agents.
klaw chat klaw start
Interactive chat or full platform with Slack integration. Zero config required.
klaw controller start klaw node join :9090 klaw dispatch "task"
Controller-node architecture. Dispatch tasks across multiple machines.
klaw build klaw run agent --task klaw ps
Run agents in Podman containers for security and reproducibility.
Get started in under a minute. No account required.
curl -fsSL https://klaw.sh/install.sh | sh