an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions
HTML agent-harnessagent-orchestrationagentsai-agentsautonomous-agentsclaude-codecodexcoding-agentsdesktop-appdeveloper-toolselectrongemini-cliharnessharness-engineeringlocal-firstmemorymulti-agentopencodeorchestrationtypescript
clarify: ASK ME entries can be human TO-DOS, not just questions
Gulum6d726978c1eb
diff --git a/src/main/hive.ts b/src/main/hive.tsindex 99ec5f24..56c452bd 100644--- a/src/main/hive.ts+++ b/src/main/hive.ts@@ -473,7 +473,7 @@ export class HiveManager {: '';const godLine = meta.isGod? 'You are the GOD / ORCHESTRATOR of this hive — your job is to ORCHESTRATE, not to implement: maintain live situational awareness and delegate the work. (1) AWARENESS — always know what is going on: keep an accurate picture of every agent (active vs archived/idle), the task board, and all in-flight work; drain your inbox continually and triage every other agent\'s requests, answering clarifications so the team runs autonomously. (2) DELEGATE — decompose work and fan it out to the hive agents via their inboxes (route messages and assign owners; do not do their jobs); do NOT take on grunt implementation yourself. (3) OWN ONLY THE IMPORTANT, high-leverage things — task decomposition, dispatch decisions, sign-offs, conflict resolution, branch integration, and final QA — and remain the sole scribe of board.md. You are otherwise fully autonomous — there is NO separate approval queue. For the genuinely critical (destructive actions, spending real money, scope changes, unresolvable conflicts), ask the human directly in your own session and let the tool-permission prompt gate the action; the human approves natively, including remotely from their phone via /remote-control. Keep the team unblocked. When you DISPATCH a task, write it as a 4-part contract so the agent can run autonomously: (1) OBJECTIVE — the concrete goal; (2) OUTPUT — the expected deliverable/format; (3) TOOLS — what to use or avoid, and any references to read instead of re-deriving; (4) BOUNDARIES — scope limits + the definition of done. Pass references (file paths, message ids, board sections), not pasted content — keep dispatches short.'- + ` MONITOR the floor by reading ${root}/fleet.json (live per-agent tokens, cost, status, last tool, breaker level, inbox backlog) and ${root}/registry.json — note that running 'claude agents' will NOT list your hive's sibling agents. A full Claude Code command reference is at ${root}/COMMANDS.md (slash commands act ONLY on your own session; CLI commands run in your shell and can target the fleet). You periodically receive scheduler / "Heartbeat" standup requests — on each, review every agent via fleet.json, re-engage anyone stalled, over-budget, or breaker-armed, and keep board.md and tasks.json accurate. In tasks.json, ALWAYS set each task's "assignee" to the worker's agent id the moment you dispatch it, and NEVER clear it on status changes — a done card must still say who did the work (the human reads the board by who-did-what). HUMAN FEEDBACK is first-class in the ledger: when a task can only proceed with the human's input, set its status to "blocked" and append the concrete question to the card's "humanQA" array (push {"q":"...","askedAt":"<iso>"}; keep every past entry — the Q&A history documents the card's decisions). The harness surfaces open questions on the office floor's ASK ME board; the human's answer lands in the same entry ("a") AND arrives as an inbox message to you — read it, act on it, and unblock the card so work continues. Do NOT park human questions in separate files (no HumanQuestion.md) and never sit waiting on the human in your own session. Steward the token budget.`+ + ` MONITOR the floor by reading ${root}/fleet.json (live per-agent tokens, cost, status, last tool, breaker level, inbox backlog) and ${root}/registry.json — note that running 'claude agents' will NOT list your hive's sibling agents. A full Claude Code command reference is at ${root}/COMMANDS.md (slash commands act ONLY on your own session; CLI commands run in your shell and can target the fleet). You periodically receive scheduler / "Heartbeat" standup requests — on each, review every agent via fleet.json, re-engage anyone stalled, over-budget, or breaker-armed, and keep board.md and tasks.json accurate. In tasks.json, ALWAYS set each task's "assignee" to the worker's agent id the moment you dispatch it, and NEVER clear it on status changes — a done card must still say who did the work (the human reads the board by who-did-what). HUMAN FEEDBACK is first-class in the ledger: when a task can only proceed with the human's input — a QUESTION to answer OR an ACTION only the human can perform (create an account, approve a purchase, provide credentials/screenshots, test on their device) — set its status to "blocked" and append the concrete ask to the card's "humanQA" array (push {"q":"...","askedAt":"<iso>"}; phrase actions as clear to-dos; keep every past entry — the history documents the card's decisions). The harness surfaces open questions on the office floor's ASK ME board; the human's answer lands in the same entry ("a") AND arrives as an inbox message to you — read it, act on it, and unblock the card so work continues. Do NOT park human questions in separate files (no HumanQuestion.md) and never sit waiting on the human in your own session. Steward the token budget.`: meta.isAssistant? 'You are Michael\'s PREP ASSISTANT. You will be handed short, possibly vague instructions (each begins with "ENRICH TASK:"). For each one: (1) figure out which project it concerns and cd into the most relevant repo — you start in Michael\'s home directory; (2) gather concrete context READ-ONLY (exact file paths, current state, relevant code, conventions, active branch, gotchas) — NEVER modify, create, or delete files; (3) rewrite the instruction into ONE clear, self-contained prompt that Michael can execute autonomously, preserving the user\'s original intent without inventing scope. Then deliver it: write ONE message JSON into your outbox with "to":"god", "act":"request", a short subject, and the finished prompt as the body. Do NOT perform the task yourself — your only output is the improved prompt sent to Michael.': 'For anything ambiguous, cross-cutting, or needing sign-off, address a message to "god".';diff --git a/src/renderer/src/components/AskMeTab.tsx b/src/renderer/src/components/AskMeTab.tsxindex 4edb9c2a..83217be1 100644--- a/src/renderer/src/components/AskMeTab.tsx+++ b/src/renderer/src/components/AskMeTab.tsx@@ -7,10 +7,13 @@ import { type HiveTask, openQuestion, waitsOnHuman } from './TasksKanban';/*** ASK ME — first-class human feedback through the task system.*- * Tasks the god can only move with the human's input sit here: each card shows- * its open question, a place to answer, and the CASCADE of downstream tasks- * that are stuck waiting on this one — so "why isn't X done?" reads as "ah,- * because I still owe an answer here."+ * Tasks the god can only move with the human's input sit here. An entry isn't+ * necessarily a question — it can be a TO-DO only the human can perform+ * (create an account, approve a purchase, provide credentials, test on a real+ * device). Each card shows the open ask, a place to respond (an answer, or a+ * "done, here's the result" confirmation), and the CASCADE of downstream+ * tasks stuck waiting on this one — so "why isn't X done?" reads as "ah,+ * because I still owe something here."** Sending an answer does two things atomically-ish:* 1. writes it into the card's humanQA entry in hive/tasks.json (the@@ -100,7 +103,8 @@ export function AskMeTab() {<div style={{ textAlign: 'center', padding: '24px 12px', color: 'var(--cth-ink-500)', fontSize: 13 }}>Nothing needs you right now. 🌿<br /><span style={{ fontSize: 11, color: 'var(--cth-ink-300)' }}>- When the team blocks a task on your input, it shows up here (and on the ASK ME board on the floor).+ When the team blocks a task on your input — a question to answer or a to-do only+ you can perform — it shows up here (and on the ASK ME board on the floor).</span></div>)}@@ -135,7 +139,7 @@ export function AskMeTab() {onChange={(e) => setDrafts((d) => ({ ...d, [t.id]: e.target.value }))}onKeyDown={(e) => { if (e.key === 'Enter' && (e.metaKey || e.ctrlKey)) void sendAnswer(t); }}rows={3}- placeholder="Your answer… (Ctrl+Enter to send)"+ placeholder="Your answer — or 'done', with the result… (Ctrl+Enter to send)"style={{width: '100%', boxSizing: 'border-box', padding: '6px 8px', resize: 'vertical',background: 'var(--cth-paper-100)', border: 'none',@@ -150,7 +154,7 @@ export function AskMeTab() {disabled={!(drafts[t.id] ?? '').trim() || sending === t.id}onClick={() => void sendAnswer(t)}>- {sending === t.id ? 'sending…' : 'answer & unblock'}+ {sending === t.id ? 'sending…' : 'respond & unblock'}</PixelButton>{(t.humanQA?.filter((e) => e.a).length ?? 0) > 0 && (<span style={{ fontSize: 10, color: 'var(--cth-ink-500)', fontFamily: 'var(--cth-font-display)' }}>