Agent operations · public-safe proof ladder

RDLeader

RDLeader is a local-first control plane for supervising multiple AI R&D workers: task ownership, progressive context, runtime dispatch, result collection, approval gates, and evidence-first QA.

The public repo is intentionally released in safe slices. It shows the architecture, contracts, fake-data demos, walkthroughs, and verification model without publishing private DevPlan paths, app IDs, chat IDs, QR artifacts, internal links, or raw live-integration logs.

TypeScript monorepo React + Vite manager UI Fastify control plane SQLite repositories ACP-style runtime dispatch Human approval gates Demo reset QA evidence 0 open configured security alerts

Copy/paste pitch: local-first control plane for AI R&D workers: task ownership, context routing, runtime evidence, approval gates, and QA.

View repository See v0.1.1 proof-ladder release Read public proof ladder Watch narrated walkthrough Use distribution kit Support RDLeader packaging Pick Tip / Proof / Review / Fund Sponsor / paid-support intake replies Sponsor prospect pipeline

Not another chat UI The focus is the operating layer around agents: ownership, context, dispatch, evidence, blocked states, and approvals.

Public-safe demos pnpm demo:reset creates deterministic fake worker, runtime, approval, and QA state for reviewers.

Architecture signal Manager UI, API, policy, brain/context assembly, ingest, runtime dispatch, and repositories are separated.

Clean security surface Current configured CodeQL, Dependabot, and secret-scanning open alerts are all 0; latest proof is linked below.

External discovery Submitted to autonomous-agent and coding-agent awesome lists; follow-up is tracked in public.

Best support note Use RDLeader #27 for external submission follow-up or RDLeader #1 for broader public-release sanitization. If you are unsure whether to tip, inspect proof, buy a review, or fund an issue, start with the 10-second support router. Support does not imply reuse rights until license posture is resolved.

What RDLeader proves

Task ownership — a worker owns a work item instead of every agent living in one undifferentiated chat stream.
Progressive context — task envelopes can assemble identity, seed, working, episodic, knowledge, and reflection layers.
Runtime evidence — dispatch, result collection, stale-task recovery, and archived runtime events are first-class concerns.
Approval boundaries — risky external actions are represented as manager-reviewable approval requests.

Dedicated employee-agent model — one worker maps to isolated runtime home and communication config in the DevPlan architecture.
QA posture — tests, smoke checks, endurance loops, browser validation, and redaction rules are summarized publicly.
Manager UI surface — overview, execution, collaboration, growth, management, QA, and ops surfaces exist in the public slice.
Honest release posture — MVP / research prototype, not a finished enterprise HR system.

Security / public-readiness proof

RDLeader's configured public security-alert surface is currently clean. This is repo-specific evidence, not a claim about older projects without equivalent analysis configured.

CodeQL open alerts: 0
Dependabot open alerts: 0
Secret-scanning open alerts: 0
Alert backlog cleanup: public DevPlan feature-bundle alerts reduced from 30 to 0.

Proof ladder

Open these in order if you only have a few minutes. The point is to make the technical claim verifiable without leaking private operational state.

Step	Public surface	What it proves
1	Public demo reset	Deterministic fake worker, work item, runtime, approval, and QA state.
2	Browser walkthrough	The fake state can be inspected through the manager UI without private seed workers.
3	Runtime / approval deep dive	Task envelopes, result events, fail-closed external actions, and recovery modes are explicit.
4	Employee-agent onboarding	Worker homes, runtime homes, manager-only communication, and secret references are documented safely.
5	QA evidence	Tests, smoke checks, endurance loops, and public redaction rules are summarized.
6	Narrated walkthrough	Public-safe visuals show the control-plane shape without DevPlan screenshots.
7	Submission tracker	Distribution and follow-up are tracked instead of handled as one-off announcements.

Architecture shape

React manager UI
      │
      ▼
Fastify control plane
      │
      ├── domain model        employees, performance, emotion, approvals
      ├── brain package       task-type → context-layer assembly
      ├── policy package      risk classification and approval gates
      ├── ingest package      git/doc memory extraction and direction knowledge
      ├── runtime package     ACP-style dispatch + result collection
      ├── ops workflows       project groups, review actions, QA reports
      └── SQLite repositories work items, messages, reflections, runtime events
      │
      ▼
Local worker workspace
  WORKSPACE_MAP.*        repo and direction map
  .rdleader/tasks        inbound task envelopes
  .rdleader/results      runtime result events

Sponsorware / follow-up surface

RDLeader#27 tracks external submission review follow-up.
RDLeader#3 tracks license posture; no root license is implied until the owner decides.
RDLeader#1 tracks broader public release and DevPlan bundle sanitization.

External PR: awesome-autonomous-agents#20.
External PR: awesome-coding-agents#13.
Support route: support RDLeader packaging work.
Public intake guardrail: use sponsor / paid-support intake replies; do not paste private logs, credentials, QR codes, payment screenshots, internal URLs, or raw live integration output in public issues.
Route by audience: use the sponsor prospect pipeline to choose the right proof, CTA, support note, and guardrail for RDLeader evaluators, curators, sponsors, and paid-review customers; then use the sponsor conversion scorecard to decide Hot / Warm / Nurture / No-send before posting.

Public-safety rule: do not publish real employee names, private workspace paths, app IDs, open IDs, chat IDs, message IDs, QR onboarding artifacts, internal document links, payment screenshots, or raw live integration output in public issues.

Copy/paste promo pack

Shortest line

RDLeader: local-first control plane for AI R&D workers — task ownership, context routing, runtime evidence, approval gates, and QA.

中文版本

RDLeader 是一个面向 AI 研发员工的本地优先控制台：任务归属、渐进式上下文、运行时派发、结果回收、审批闸门和 QA 证据，而不是又一个聊天窗口。

English version

RDLeader is a local-first control plane for supervising AI R&D workers. It focuses on what happens after multiple agents are running: who owns the task, what context was loaded, what runtime ran it, what result came back, what is blocked, and which actions need approval.

Best 3-link pack

Repo: https://github.com/happysnaker/RDLeader
Project page: https://happysnaker.github.io/rdleader/
Proof ladder: https://github.com/happysnaker/RDLeader/blob/main/docs/public/landing-page.md