Kipple Labs
Kiger · OpenClaw-compatible

A hardened AI agent with a full operator console.

Kiger is Kipple Labs' agent runtime — a hardened AI agent, sandboxed, with a real console. Run it on your laptop, deploy it to your own cloud server, or have us host it — it's the same agent either way. Capability-scoped tools, multi-model routing, memory, and voice, all under your control.

Capability-sandboxed Multi-model routing Desktop · browser · mobile Voice Built on AXIS
Capability sandbox

Every skill says what it can touch — and nothing else works.

Declare capabilities, not permissions

Each skill declares exactly which network hosts, files, secrets, commands, and channels it may reach — six axes, default-deny. Anything it didn't declare is unreachable, even if the model asks.

Real isolation for WASM skills

Skills compiled to WebAssembly run in a wasmtime sandbox with per-skill fuel and memory limits — a hard boundary around untrusted code.

Workspace ceilings

Operators set a maximum capability ceiling per workspace. An agent's config can only narrow it — never widen past what you approved.

Elevation-class approvals

Writing files, running commands, or spending money needs a signed approval on file first. Approvals are keyed to the exact capability surface, so a real change re-prompts.

Secrets stay out of reach

Credentials resolve from your OS keychain or 1Password — never the agent's environment. Credential-shaped paths like .env, *.key, and id_rsa are refused even inside an allowed folder.

Signed skills

Every skill ships with an Ed25519-signed manifest and per-file hashes. Tamper with a skill and the runtime refuses to load it.

web-search · SKILL.md
WASM SIGNED NET:8 SECRETS:5 FS:0 EXEC:0
network api.brave.com:443
secrets brave-api-key
filesystem
exec
deny · .env *.key id_rsa
CLI + operator console

CLI for builders. Console for operators.

Develop in the terminal when you're tinkering. Operate from desktop, browser, or mobile when you're running it. Kiger is both — same agent, same configuration, wherever you are.

All your agents, one view

A fleet overview shows every agent — its status, skills, and recent activity — without opening a config file.

The console goes with you

Approve an action from your laptop. Check the audit trail on your phone. The same console runs in the browser, as a desktop tray app, or on your phone — your agent doesn't stop when you step away from your desk.

Flip skills on and off live

Enable or disable a skill without redeploying. It takes effect on the agent's next loop tick — no restart, no config edit.

Approval queue & lockdown

Actions that need sign-off surface with a live badge — grant or deny in a click. Freeze an agent's risky capabilities with a time-boxed lockdown when you need to.

Chat, sessions, and projects

Per-agent threads grouped into projects with their own instructions and files, plus a memory panel showing what the agent actually knows.

A CLI for builders

Build and script from the terminal — mint tokens, install skills, run the daemon, open a secure tunnel. Then operate from the console when it's running. Kiger is both.

kiger · operator console
FleetChatAgentsApprovalsSkillsAuditDoctor
Desktop Browser Mobile
Model routing

Route every turn to the right model — and see the bill.

Bring any provider

Anthropic, OpenAI, Gemini and Vertex, local Ollama, and OpenAI-compatible models like DeepSeek, Qwen, and GLM — mixed however you like.

Tiered routing

Simple, moderate, and deep tiers map to the models you pick. Each turn is classified and routed — by fast heuristics, a small cloud or local classifier, or a hybrid of both.

A cost and token ledger

Every call is logged with its tier, token counts, and estimated cost — so you always know which agent is expensive and why.

Fallback and circuit breakers

A provider outage falls through to your backup chain instead of dropping the turn — with a breaker that stops hammering a failing endpoint.

Audit · routing log
07:55simple haiku · very-short3580→224
07:54moderate sonnet · default18360→5418
07:18simple haiku · yesno9838→6158
06:35moderate sonnet · coding-task36629→5392
Voice

Talk to your agents. Hear them answer.

A push-to-talk console with spoken replies — usable like a call, metered like everything else.

Push-to-talk dictation

Speak in the browser with on-device speech recognition, with a Whisper fallback for browsers that don't have it.

Spoken replies & a call overlay

Agents speak back with a per-voice character, and a voice overlay turns a chat thread into a back-and-forth conversation.

Every second metered

Speech and voice cost is written to a ledger and shown live in the chat status line — no surprise voice bill.

Voice-tuned routing

Voice turns default to a faster, terser model so replies come back quickly — the classifier can still promote a hard question.

Memory

Agents that remember — and can show their work.

Episodic + semantic recall

Agents save what matters and recall it by keyword or by meaning, using local embeddings — with a graceful fallback when the embedding model is offline.

An Obsidian-shaped notes vault

Each agent keeps a markdown vault with frontmatter and wikilinks it can write to and query.

A typed ontology

People, projects, and tasks as first-class entities with relations — so "who else is on this project?" has a real answer.

A personal library

Ingest documents and papers per agent and search them, so answers can be grounded in real sources.

Identity & audit

Know which agent did what — and prove it.

Per-agent identity

Every agent carries its own Ed25519 keypair, and high-trust actions are wrapped in signed envelopes that break if tampered with.

Delegation chains

When one agent invokes another, the authority chain is recorded — trace any downstream action back to the instruction that started it.

An append-only audit log

Channel, tier, model, tokens, steps, tools, and time for every turn — persisted outside the agent, so restarting it never erases the history.

AXIS-ready, when you want it

Opt in and agents carry portable AXIS Protocol identity across organizations. It's off by default — you decide when cross-org identity turns on.

Reach

Meet your agents where you already are.

Two-way chat channels, connectable tools, and secure remote access — all under the same capability rules.

Slack, Telegram & Discord — two-way

Allowlisted people message an agent directly in Slack, Telegram, or Discord — full routing and memory, with approval cards inline. Fail-closed: unknown senders can't get in.

Email & webhooks out

Agents send email and post to webhooks through the channel router — the skill names a target, and you map where it actually goes.

Connect MCP servers

Point an agent at an MCP server and its tools join the agent's catalog, authenticated per call.

Remote access, no open ports

Reach your agents over a Cloudflare Tunnel with a remote-scoped token — nothing exposed to the open internet.

How it fits together

One runtime, three layers.

Kiger is the runtime. AXIS gives each agent an identity. Owyhee is the governance layer its calls run through. Each layer stands on its own — together they make an agent you can hand real access to.

Kiger
The runtime

The agent itself — capability sandbox, model routing, memory, voice, and the operator console. Deploy it yourself, or have us run it.

Deploy an agent →
AXIS
The identity

An open protocol that gives an agent a signed, verifiable identity and a delegation chain back to you. Opt in when you want identity that travels across organizations.

About AXIS →
Owyhee
The governance layer

Kiger agents connect through Owyhee for governed access — credentials in custody, grants scoped to exactly what you allow (say, content:comment on one site), and a receipt for every call. Revoke, and it stops.

What Owyhee adds →
Ways to run it

Deploy it yourself, or have it hosted.

Self-deploy
Guided path · live today

The guided deploy path walks you through standing up a governed agent on a small cloud server — or your own machine — step by step. The Owyhee-hardened OpenClaw agent is in the catalog now; Kiger is next in.

Start deploying →
One-click on DigitalOcean
Coming soon

A native 1-Click that stands an agent up on a droplet you own — nothing to configure. The Marketplace listing is in review.

Get notified →
Hosted by Kipple Labs
Early access

We run Kiger for you; you drive it from the console. While it's early, onboarding is hands-on with us — write and we'll set you up.

Request early access →

Get started with Kiger.

Free to run. Deploy an agent yourself from the guided path, or ask us about hosted early access. Add Owyhee when you're ready to hand it real access.