Seeded INTENT.md and some basic information.
This commit is contained in:
parent
281c702a7d
commit
1381f29904
6 changed files with 480 additions and 0 deletions
176
AGENTS.md
Normal file
176
AGENTS.md
Normal file
|
|
@ -0,0 +1,176 @@
|
|||
# polycode-sim — Agent Instructions
|
||||
|
||||
## Repo Identity
|
||||
|
||||
**Purpose:** PolyCode Simulator is a Python-based agent simulation modeling investor and voter strategies to study governance/allocation dynamics, with parameter sweeps and KPI aggregation.
|
||||
|
||||
**Domain:** infotech
|
||||
**Repo slug:** polycode-sim
|
||||
**Topic ID:** `cee7bedf-2b48-46ef-8601-006474f2ad7a`
|
||||
**Workplan prefix:** `POLYCODE-WP-`
|
||||
|
||||
---
|
||||
|
||||
## State Hub Integration
|
||||
|
||||
The Custodian State Hub tracks work across all domains. Interact via HTTP REST —
|
||||
there is no MCP server for Codex agents.
|
||||
|
||||
| Context | URL |
|
||||
|---------|-----|
|
||||
| Local workstation | `http://127.0.0.1:8000` |
|
||||
| Remote via tunnel | `http://127.0.0.1:18000` |
|
||||
| Optional local edge relay | http://127.0.0.1:18080 |
|
||||
|
||||
When an operator has enabled the edge relay, set API_BASE to the relay URL.
|
||||
Queueable writes return an explicit queued receipt if the central hub is
|
||||
unreachable. Treat that as pending local evidence, then ask the operator to run
|
||||
statehub outbox status/replay after connectivity returns.
|
||||
|
||||
### Orient at session start
|
||||
|
||||
```bash
|
||||
# Offline brief — works without hub connection
|
||||
cat .custodian-brief.md
|
||||
|
||||
# Active workplans for this domain
|
||||
curl -s "http://127.0.0.1:8000/workplans/?topic_id=cee7bedf-2b48-46ef-8601-006474f2ad7a&status=active" \
|
||||
| python3 -m json.tool
|
||||
|
||||
# Check inbox
|
||||
curl -s "http://127.0.0.1:8000/messages/?to_agent=polycode-sim&unread_only=true" \
|
||||
| python3 -m json.tool
|
||||
```
|
||||
|
||||
Mark a message read:
|
||||
```bash
|
||||
curl -s -X PATCH "http://127.0.0.1:8000/messages/<id>/read" \
|
||||
-H "Content-Type: application/json" -d '{}'
|
||||
```
|
||||
|
||||
### Log progress (required at session close)
|
||||
|
||||
```bash
|
||||
curl -s -X POST http://127.0.0.1:8000/progress/ \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"summary": "what was done",
|
||||
"event_type": "note",
|
||||
"author": "codex",
|
||||
"workplan_id": "<uuid>",
|
||||
"task_id": "<uuid>"
|
||||
}'
|
||||
```
|
||||
|
||||
Omit `workplan_id` / `task_id` when not applicable.
|
||||
|
||||
### Update task status
|
||||
|
||||
```bash
|
||||
curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"status": "progress"}'
|
||||
# values: wait | todo | progress | done | cancel
|
||||
```
|
||||
|
||||
### Flag a task for human review
|
||||
|
||||
```bash
|
||||
curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"needs_human": true, "intervention_note": "reason"}'
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Session Protocol
|
||||
|
||||
**Start:**
|
||||
1. `cat .custodian-brief.md` — domain goal and open workplans (offline-safe)
|
||||
2. Check inbox: `GET /messages/?to_agent=polycode-sim&unread_only=true`; mark read
|
||||
3. Scan workplans: `ls workplans/` — note `status: ready`, `active`, or `blocked` files and open tasks
|
||||
4. Check human-needed tasks: `GET /tasks/?needs_human=true`
|
||||
|
||||
**During work:**
|
||||
- Update task statuses in workplan files as tasks progress
|
||||
- Record significant decisions via `POST /decisions/`
|
||||
|
||||
**Close:**
|
||||
1. Update workplan file task statuses to reflect progress
|
||||
2. Log: `POST /progress/` with a summary of what changed
|
||||
3. After workplan file changes, run:
|
||||
```bash
|
||||
statehub fix-consistency
|
||||
```
|
||||
Coding agents should run this directly; ask the operator only if the CLI or
|
||||
State Hub API is unavailable. This syncs task status from files into the hub DB.
|
||||
|
||||
---
|
||||
|
||||
{CREDENTIAL_ROUTING}
|
||||
|
||||
<!-- REPO-AGENTS-EXTENSIONS -->
|
||||
<!-- Append repo-specific agent instructions below this marker.
|
||||
The state-hub template sync preserves content after this line. -->
|
||||
|
||||
---
|
||||
|
||||
## Workplan Convention (ADR-001)
|
||||
|
||||
Work items originate as files in this repo — not in the hub. The hub is a
|
||||
read/cache/index layer that rebuilds from files.
|
||||
|
||||
**File location:** `workplans/POLYCODE-WP-NNNN-<slug>.md`
|
||||
|
||||
**Archived location:** finished workplans may move to
|
||||
`workplans/archived/YYMMDD-POLYCODE-WP-NNNN-<slug>.md`. The `YYMMDD` prefix is
|
||||
the completion/archive date; the frontmatter `id` does not change.
|
||||
|
||||
**Ad Hoc Tasks:** small opportunistic fixes discovered during a session use
|
||||
`workplans/ADHOC-YYYY-MM-DD.md` with task ids `ADHOC-YYYY-MM-DD-T01`, etc. Use
|
||||
this only for low-risk work completed directly; create a normal workplan for
|
||||
anything needing analysis, design, approval, dependencies, or multiple phases.
|
||||
|
||||
**Frontmatter:**
|
||||
|
||||
```yaml
|
||||
---
|
||||
id: POLYCODE-WP-NNNN
|
||||
type: workplan
|
||||
title: "..."
|
||||
domain: infotech
|
||||
repo: polycode-sim
|
||||
status: proposed | ready | active | blocked | backlog | finished | archived
|
||||
owner: codex
|
||||
topic_slug: ...
|
||||
created: "YYYY-MM-DD"
|
||||
updated: "YYYY-MM-DD"
|
||||
state_hub_workstream_id: "<uuid>" # written by fix-consistency — do not edit (legacy name; holds the workplan id)
|
||||
---
|
||||
```
|
||||
|
||||
Use `proposed` for a new draft, `ready` after review against current repo
|
||||
state, and `finished` after implementation. `stalled` and `needs_review` are
|
||||
derived health labels, not frontmatter statuses.
|
||||
|
||||
**Task block format** (one per `##` section):
|
||||
|
||||
```
|
||||
## Task Title
|
||||
|
||||
` ` `task
|
||||
id: POLYCODE-WP-NNNN-T01
|
||||
status: wait | todo | progress | done | cancel
|
||||
priority: high | medium | low
|
||||
state_hub_task_id: "<uuid>" # written by fix-consistency — do not edit
|
||||
` ` `
|
||||
|
||||
Task description text.
|
||||
```
|
||||
|
||||
Status progression: `todo` → `progress` → `done`; use `wait` for waiting/blocked work and `cancel` for stopped work.
|
||||
|
||||
To create a new workplan:
|
||||
1. Write the file following the format above
|
||||
2. Run `statehub fix-consistency` locally; ask the operator only if the CLI or
|
||||
State Hub API is unavailable.
|
||||
23
INTENT.md
Normal file
23
INTENT.md
Normal file
|
|
@ -0,0 +1,23 @@
|
|||
**PolyCode Simulator** is a research/prototyping tool for exploring how different stakeholder behaviors affect governance and resource allocation outcomes.
|
||||
|
||||
More concretely:
|
||||
|
||||
**PolyCode Simulator** is a Python simulation system where different types of agents, especially **investors** and **voters**, follow configurable strategies. These agents interact inside a modeled governance or allocation environment. By changing parameters repeatedly, the simulator can explore many scenarios and collect KPIs that show how well different governance/allocation mechanisms perform.
|
||||
|
||||
In practical terms, it should do four things:
|
||||
|
||||
1. **Models actors**
|
||||
Investors may allocate capital, back proposals, seek returns, or influence outcomes. Voters may support proposals, delegate votes, behave strategically, or vote based on preferences.
|
||||
|
||||
2. **Models governance/allocation rules**
|
||||
It studies how resources, funding, influence, votes, or rewards are distributed under different mechanisms.
|
||||
|
||||
3. **Runs experiments**
|
||||
Parameter sweeps mean it systematically varies assumptions such as number of voters, investor behavior, voting rules, capital distribution, turnout, strategy mix, incentives, or governance thresholds.
|
||||
|
||||
4. **Aggregates results**
|
||||
KPI aggregation means it summarizes outcomes across runs, for example efficiency, fairness, concentration of power, proposal success rate, capital allocation quality, voter satisfaction, resilience, or strategic exploitability.
|
||||
|
||||
Polycode is a **simulation laboratory for mechanism design**: a way to test governance and funding systems before deploying them in the real world.
|
||||
|
||||
|
||||
|
|
@ -1,5 +1,7 @@
|
|||
# PolyCode Simulator (v0.1)
|
||||
|
||||
Simulator for PolyCode Market Dynamics
|
||||
|
||||
## Quickstart
|
||||
|
||||
1) Run a single demo simulation:
|
||||
|
|
|
|||
36
SCOPE.md
Normal file
36
SCOPE.md
Normal file
|
|
@ -0,0 +1,36 @@
|
|||
# SCOPE
|
||||
|
||||
> This file was generated by `statehub register`. Refine it as the repository
|
||||
> boundaries become clearer.
|
||||
|
||||
## One-liner
|
||||
|
||||
PolyCode Simulator is a Python-based agent simulation framework for studying governance and resource-allocation dynamics. It models investor and voter strategies, runs parameterized scenario sweeps, and aggregates KPIs to compare the behavior, robustness, and outcomes of different allocation mechanisms.
|
||||
|
||||
## Core Idea
|
||||
|
||||
Polycode is a simulation laboratory for mechanism design: a way to test governance and funding systems before deploying them in the real world.
|
||||
|
||||
## In Scope
|
||||
|
||||
- Core simulation engine for a single demo run
|
||||
- Pluggable investor/voter strategy modules
|
||||
- Parameter sweeps and KPI aggregation via experiments.py
|
||||
- Baseline parameter configuration management
|
||||
- Protocol specification documentation
|
||||
|
||||
## Out of Scope
|
||||
|
||||
- Production/live deployment integration
|
||||
- Visualization dashboard or UI
|
||||
- Cross-repo orchestration
|
||||
|
||||
## Current State
|
||||
|
||||
- {"project_description": "PolyCode Simulator is a Python-based agent simulation modeling investor and voter strategies to study governance/allocation dynamics, with parameter sweeps and KPI aggregation.", "intent_markdown": "# Intent\n\n## Purpose\nPolyCode Simulator (v0.1) is a Python simulation engine that models interactions between investor and voter agents under pluggable strategies, used to explore governance and capital-allocation dynamics and their emergent outcomes (KPIs) across parameter sweeps.\n\n## In Scope\n- Core simulation engine (`simulator.py`) running single demo simulations\n- Pluggable investor/voter strategy implementations (`strategies.py`)\n- Parameter sweep / grid-search experiments with KPI aggregation (`experiments.py`)\n- Baseline parameter configuration (`params_default.json`)\n- Protocol specification documentation (`spec.md`)\n- Run outputs written to `./runs/`\n\n## Out of Scope\n- Production deployment or live trading/voting integration\n- UI/dashboard for visualizing results\n- Multi-repo orchestration or external service integration\n\n## Current State\nEarly-stage (v0.1) simulator with a minimal CLI-driven workflow; single initial commit plus a CI smoke workflow.\n", "domain_slug": null, "topic_slug": "polycode-sim", "topic_title": "PolyCode Simulator", "repo_slug": "polycode-sim", "workplan_prefix": "POLYCODE-WP", "in_scope": ["Core simulation engine for a single demo run", "Pluggable investor/voter strategy modules", "Parameter sweeps and KPI aggregation via experiments.py", "Baseline parameter configuration management", "Protocol specification documentation"], "out_of_scope": ["Production/live deployment integration", "Visualization dashboard or UI", "Cross-repo orchestration"], "project_description": "PolyCode Simulator is a Python-based agent simulation modeling investor and voter strategies to study governance/allocation dynamics, with parameter sweeps and KPI aggregation.", "repo_slug": "polycode-sim", "topic_slug": "polycode-sim", "topic_title": "PolyCode Simulator", "workplan_prefix": "POLYCODE-WP"}
|
||||
|
||||
## Getting Oriented
|
||||
|
||||
- Start with: INTENT.md
|
||||
- Agent instructions: AGENTS.md
|
||||
- Workplans: workplans/
|
||||
184
specs/PolyCodePitchDeck
Normal file
184
specs/PolyCodePitchDeck
Normal file
|
|
@ -0,0 +1,184 @@
|
|||
PolyCode
|
||||
|
||||
*Predict. Invest. Build. Together.*
|
||||
|
||||
# 📘 PolyCode — Pitch Deck (v0.1)
|
||||
|
||||
---
|
||||
|
||||
## 1. Title Slide
|
||||
|
||||
**PolyCode**
|
||||
**The AI-Driven Market Where Code Funds Itself**
|
||||
Predict. Invest. Build. Together.
|
||||
|
||||
*(Logo placeholder)*
|
||||
|
||||
---
|
||||
|
||||
## 2. The Problem
|
||||
|
||||
Modern software development is:
|
||||
|
||||
* Slow — coordination and funding bottlenecks stall innovation.
|
||||
* Opaque — investors and contributors can’t see progress or ROI until it’s too late.
|
||||
* Top-down — product priorities are decided by a few, not by the ecosystem that needs them.
|
||||
|
||||
> **We need a market where ideas compete fairly and resources flow to what proves valuable.**
|
||||
|
||||
---
|
||||
|
||||
## 3. The Vision
|
||||
|
||||
**PolyCode** transforms software creation into a self-financing, self-correcting economy.
|
||||
A decentralized platform where:
|
||||
|
||||
* Ideas are posted as *issues*.
|
||||
* Users invest and predict the effort required.
|
||||
* AI agents implement once funding thresholds are met.
|
||||
* Adoption validates success and triggers automatic payouts.
|
||||
|
||||
> **Software builds itself — guided by markets, not managers.**
|
||||
|
||||
---
|
||||
|
||||
## 4. How It Works (Simplified Flow)
|
||||
|
||||
1️⃣ **Post an Idea**
|
||||
→ Anyone creates an issue (feature, fix, or concept).
|
||||
|
||||
2️⃣ **Invest & Predict**
|
||||
→ Backers fund the idea and bet on required effort + time.
|
||||
|
||||
3️⃣ **AI Implementation Begins**
|
||||
→ When funding exceeds predicted effort, PolyCode assigns it to an AI developer instance.
|
||||
|
||||
4️⃣ **Community Votes on Decisions**
|
||||
→ AI proposes variants; investors vote.
|
||||
|
||||
5️⃣ **Control Point Review**
|
||||
→ At 50% budget use, progress is published — investors can withdraw or double down.
|
||||
|
||||
6️⃣ **Deployment & Adoption Test**
|
||||
→ Feature released under a flag.
|
||||
→ If >50% of users keep it → accepted & payouts distributed.
|
||||
|
||||
---
|
||||
|
||||
## 5. Reward Distribution (Example)
|
||||
|
||||
| Recipient | Share | Motivation |
|
||||
| --------------- | ---------------- | -------------------- |
|
||||
| Top estimators | 10 % + 5 % + 1 % | Reward accuracy |
|
||||
| Issue author | 10 % | Encourage creativity |
|
||||
| Decision voters | 8 % | Reward participation |
|
||||
| Investors | 50 % | Return on capital |
|
||||
| Platform | up to 16 % | Sustain operations |
|
||||
|
||||
---
|
||||
|
||||
## 6. Example Simulation Outcome
|
||||
|
||||
From early **PolyCode Sim v0.1** runs:
|
||||
|
||||
* 75 % of issues reach acceptance threshold.
|
||||
* 20 % overspend frequency (indicates healthy risk dispersion).
|
||||
* Decision-quality correlation = +0.42 with adoption (market voting works).
|
||||
* Manipulation-proxy < 0.1 mean (robust estimate integrity).
|
||||
|
||||
> Simulation validates that **market feedback can guide AI development efficiently**.
|
||||
|
||||
---
|
||||
|
||||
## 7. Technology Stack
|
||||
|
||||
| Layer | Description |
|
||||
| -------------------- | ------------------------------------------------------------ |
|
||||
| **PolyCode Sim** | Agent-based simulator for economic tuning |
|
||||
| **Core Protocol** | Funding, betting, voting, payout logic |
|
||||
| **AI Agents** | Claude Code / OpenAI Codex / local LLMs |
|
||||
| **Governance Layer** | DAO-like voting & reputation system |
|
||||
| **Telemetry** | Live metrics from production feed simulator for optimization |
|
||||
|
||||
---
|
||||
|
||||
## 8. Competitive Landscape
|
||||
|
||||
| Model | Example | Limitations | PolyCode Advantage |
|
||||
| -------------------- | ------------------ | ------------------------ | ------------------------------- |
|
||||
| Freelance Platforms | Upwork, Fiverr | Manual, trust-based | Automated, prediction-verified |
|
||||
| Crowdfunding | Kickstarter | No delivery verification | Code shipped + adoption proof |
|
||||
| Open Source Bounties | Gitcoin | Low iteration speed | Continuous, AI-assisted cycles |
|
||||
| AI Dev Tools | Replit Ghostwriter | No funding market | Integrated economy + governance |
|
||||
|
||||
---
|
||||
|
||||
## 9. Economic Engine
|
||||
|
||||
PolyCode introduces **three internal currencies**:
|
||||
|
||||
| Token | Function |
|
||||
| ----------------- | -------------------------------------------------- |
|
||||
| **$VIBE / $WORK** | Implementation energy — tokens representing effort |
|
||||
| **$BET** | Prediction stakes for estimating scope and time |
|
||||
| **$IMPACT** | Earned reputation for successful participation |
|
||||
|
||||
A balanced micro-economy ensures liquidity, accountability, and transparent reward flows.
|
||||
|
||||
---
|
||||
|
||||
## 10. Business Model
|
||||
|
||||
1. **Transaction fees** on each completed issue (platform share).
|
||||
2. **Premium analytics / dashboards** for investors and DAOs.
|
||||
3. **Enterprise integration** — companies host private PolyCode markets.
|
||||
4. **Token appreciation** via protocol usage and staking.
|
||||
|
||||
---
|
||||
|
||||
## 11. Go-to-Market Plan
|
||||
|
||||
* **Phase 1:** Closed beta with AI-assisted open-source repos.
|
||||
* **Phase 2:** Public market for micro-features.
|
||||
* **Phase 3:** Enterprise & DAO integration.
|
||||
* **Phase 4:** On-chain economy with live telemetry feedback.
|
||||
|
||||
---
|
||||
|
||||
## 12. Team & Ecosystem
|
||||
|
||||
* **Founder:** Bernd Worsch — Product strategist, hybrid-post innovator, AI systems architect.
|
||||
* **Core Collaborators:** AI agents, open-source devs, research partners.
|
||||
* **Allies:** Coulomb ecosystem (Charges & Joules currencies), KaizenAgentic framework.
|
||||
|
||||
---
|
||||
|
||||
## 13. Traction & Next Steps
|
||||
|
||||
✅ Simulation engine operational.
|
||||
✅ Parameter optimization underway.
|
||||
🔜 Beta testers onboarding Q1 2026.
|
||||
🔜 Telemetry loop integration for adaptive tuning.
|
||||
|
||||
> **We’re validating an entirely new way to build software.**
|
||||
|
||||
---
|
||||
|
||||
## 14. The Ask
|
||||
|
||||
We are seeking:
|
||||
|
||||
* **€500 k** pre-seed for platform launch & compliance.
|
||||
* Partnerships with **AI infrastructure providers** and **early-stage DAOs**.
|
||||
* Strategic advisors in **game theory**, **token economics**, and **open-source ecosystems**.
|
||||
|
||||
---
|
||||
|
||||
## 15. Closing
|
||||
|
||||
> “In PolyCode, ideas don’t wait for permission —
|
||||
> they attract belief, code themselves, and prove their worth.”
|
||||
|
||||
**polycode.ai** | *Predict – Invest – Build – Together*
|
||||
|
||||
xxx
|
||||
59
workplans/POLYCODE-WP-0001-statehub-bootstrap.md
Normal file
59
workplans/POLYCODE-WP-0001-statehub-bootstrap.md
Normal file
|
|
@ -0,0 +1,59 @@
|
|||
---
|
||||
id: POLYCODE-WP-0001
|
||||
type: workplan
|
||||
title: "Bootstrap State Hub integration"
|
||||
domain: infotech
|
||||
repo: polycode-sim
|
||||
status: ready
|
||||
owner: codex
|
||||
topic_slug: custodian
|
||||
created: "2026-07-08"
|
||||
updated: "2026-07-08"
|
||||
state_hub_workstream_id: "05e27f85-6a20-4906-a3c1-633776d6c448"
|
||||
---
|
||||
|
||||
# Bootstrap State Hub integration
|
||||
|
||||
PolyCode Simulator is a Python-based agent simulation modeling investor and voter strategies to study governance/allocation dynamics, with parameter sweeps and KPI aggregation.
|
||||
|
||||
## Review Generated Integration Files
|
||||
|
||||
```task
|
||||
id: POLYCODE-WP-0001-T01
|
||||
status: todo
|
||||
priority: high
|
||||
state_hub_task_id: "d0f6a1cd-641f-4a63-890c-99bc5c12cc4b"
|
||||
```
|
||||
|
||||
Review `INTENT.md`, `SCOPE.md`, `AGENTS.md`, and `.custodian-brief.md`.
|
||||
Replace generated placeholders with repo-specific facts where needed.
|
||||
|
||||
## Verify Local Developer Workflow
|
||||
|
||||
```task
|
||||
id: POLYCODE-WP-0001-T02
|
||||
status: todo
|
||||
priority: high
|
||||
state_hub_task_id: "6ad22e61-ad4d-4643-ad49-000e41e4959b"
|
||||
```
|
||||
|
||||
Identify the repo's install, test, lint, build, and run commands. Add or refine
|
||||
those commands in the agent instructions so future coding sessions can verify
|
||||
changes confidently.
|
||||
|
||||
## Seed First Real Workplan
|
||||
|
||||
```task
|
||||
id: POLYCODE-WP-0001-T03
|
||||
status: todo
|
||||
priority: medium
|
||||
state_hub_task_id: "d0d8fea2-28e8-4766-8295-9118a8378c2c"
|
||||
```
|
||||
|
||||
Create the first implementation workplan for the repository's most important
|
||||
next change. After workplan file updates, run the sync locally from this repo
|
||||
checkout:
|
||||
|
||||
```bash
|
||||
statehub fix-consistency
|
||||
```
|
||||
Loading…
Add table
Add a link
Reference in a new issue