BetaNow in private betaThe unified AI agent workspace, now in private beta

One workspace. Every AI agent.
Working as one team.

AI agents and people share context, delegate and transfer tasks, and stay accountable for every result.

One workspace
All your AI agents work together in one place.
Seamless handoffs
Work and context move between agents and people.
Clear ownership
Every action, decision and code change is traceable.

Fix double loyalty discountcheckout-service

Loyalty discounts apply twice on bundled items. Fix it, add a regression test, and update the pricing docs.

Worked for 12s

Found it: applyBundleRules() applies the loyalty rate again after applyLoyalty() already did. I'll fix it here and delegate the test and the docs so they run in parallel.

Delegates2 working1 working · 1 ready to merge1 merged · 1 working

Regression test for bundlesorkilab/chat/4f2a9c1e+42 −0WorkingMergeMerged

Update the pricing docsorkilab/chat/b81d07e3Working

Codex's test fails on main and passes with the fix. Merging its patch now; I'll open the PR as soon as Cursor's docs land.

Message Claude Code… (/ for commands and skills, ! for shell)

Default model

Works with the agents you already use

12 today, plus any agent on the open ACP standard.

Claude Code
Codex
Cursor
OpenCode
Google Antigravity
Devin CLIACP
Grok BuildACP
DeepSeek HarnessACP
Kimi CodeACP
MiniMax CodeACP
ZCodeACP
PiACP
Any ACP agent

The problem

AI agents work in silos. OrkiLab brings them together.

Message Claude Code…same brief, again

Message Cursor…same brief, again

Message Codex…same brief, again

01 · One person, many agents

The same brief, every time

Each agent starts from zero.

Dev A

Bundle pricing

Loyalty rules

Dev B

Port modal

Checkout copy

02 · A team on one agent

Context remains siloed

Decisions stay locked on one laptop.

Why does bundles.ts skip the loyalty check?

The answer is in Dev A's sessionnot shared

03 · A team on different agents

Eliminate repetitive context sharing

Shared knowledge across agents.

Delegation

Agents that ask each other for help. During active workflows.

Claude Codelead · delegates 3 tasks
Codex--wait
Why does applyLoyalty() run twice?
Answered
Cursor--need figma --write
Match the checkout modal to the Figma frame
Ready to merge
OpenCode--best-of 3 --write
Speed up price calculation
Merged best of 3

Wait
--wait
Get the answer, then continue.
Background execution
default
Keep working. Collect it later.
Parallel execution
--harness ×N
One task, several agents.
Intelligent task routing
--need
The agent with the right tools.

Handoff

Switch agents during active workflows. Lose nothing.

The full conversation, summarized
Decisions and constraints
Files and unsaved changes too

Make the cache production readycache

Enforce the 64 MB limit in lru.rs and evict before inserting.

Added a byte-based budget and eviction in src/cache/lru.rs. Two tests are still red; the edge cases need a closer look at the UI that reads the cache.

Continued on Cursor · carried pack vd2e1f2f, 2 summaries, last 2 messages

Message Claude Code… (/ for commands and skills, ! for shell)

Message Cursor… (/ for commands and skills, ! for shell)

Default model

Continue on another harness

A new chat on the harness you pick takes over this Claude Code chat's work. It starts from the compressed conversation instead of a blank slate.

Codexsigned in

Cursorsigned in

OpenCodesigned in

Carrying

pack vd2e1f2f (0.5 KB) · 2 summaries · last 2 messages · state block

Files and unsaved changes move with it.

CancelContinue on CodexContinue on Cursor

Collaboration rooms

One room for your team and all of its agents.

cacheMake the cache production ready main WORKTRUNKMRPRLive

src/cache/lru.rs 2 editing

12pub fn insert(&mut self, key: String, val: Vec<u8>) {

13 let size = key.len() + val.len();

14 while self.bytes + size > self.limit {Priya

15 self.evict_oldest();

16 }

17 self.bytes += size;

18 self.map.insert(key, val);

19 debug_assert!(self.bytes <= self.limit);Claude Code

20}

Live, together
Every cursor, human or agent.
One board
Assign tasks to any agent.
Always caught up
Update a stale agent in one click.

pricing/bundles.ts Traceability

Claude Code3w1export function applyBundleRules(cart: Cart): Cart {

2 const bundles = groupBundles(cart.items);

Codex3w3 for (const b of bundles) {

AArjun2w4 if (b.loyaltyApplied) continue;

Codex3w5 b.price = b.price * (1 - cart.loyaltyRate);

6 }

PPriyalive7 // loyalty is applied once, upstream in applyLoyalty()

Claude Code3w8 return withTotals(cart, bundles);

9}

10

11function withTotals(cart: Cart, bundles: Bundle[]) {

12 const subtotal = sum(bundles.map((b) => b.price));

13 return { ...cart, bundles, subtotal };

14}

Codexdelegate3 weeks ago

Task “Bundle pricing rules”, delegated by Claude Code

commit 76ffd1d · merged by Arjun

“Loyalty is applied upstream, so bundles can apply it directly.”

Open conversation

● Claude Code 44%● Codex delegate 33%● Arjun 12%● Priya, live 11%

Code & Contribution Traceability

Know who wrote every line. Agent or person.

Agent, model, session or person
Even edits not yet saved
One click to the conversation behind it

Developers

Built for the terminal, too.

One CLI: orkilab agent. For agents, scripts and CI.

~/checkout-service

❯ orkilab agent delegate --need figma --explain "Match the checkout modal to the Figma frame"

checking ready harnesses for a skill, plugin or MCP server named figma

cursor figma MCP · ready · preferred for UI work

claude-code no match

→ routed to cursor (delegate chat_b81d07e3)

Under the hood

Everything else. Local by default.

Needs review · 1

The cache must stay under 64 MB

Constraint found by Claude Code

Accept AcceptedNow in every agent's contextReject

Shared project knowledge

Review a finding once. Every agent knows it.

Context window38.5k / 1M

Compaction window38.5k / 80k

Summaries: 1 · 9.2k → 1.3k tokens

Intelligent context management

Long sessions, compressed. Nothing important lost.

loyalty

pnpm test bundlesfailed
pricing/bundles.tsedit
“Loyalty applies once, before…”reply

Unified activity timeline

Every command and edit, searchable.

main +72 −0

orkilab/chat/4f2a9c1e

orkilab/chat/b81d07e3

Isolated execution environments

Parallel work that never collides.

Runs on your machine

Your code and sessions stay local.

Open to any agent

Any agent on the open ACP standard.

Coming next

Orki Bots. Something new is joining your agent team.

In the works. Waitlist sees it first.

Get notified Next in line after the beta

Explain it once. Let your agents handle the rest.

Private beta, opening in small batches.

One workspace. Every AI agent. Working as one team.