The Journey Ahead

Every region on this map is a milestone. The path glows where we've been.

Last updated: 2026-04-13
33% Overall
Complete
In Progress
Planned
0
Phase 0 The Clearing 100%
Veloren Fork
Forked & customized 3D voxel RPG engine (Rust, GPL-3)
Custom Server Mod
Agent component, TCP bridge, spectator cam, world bounds, perpetual noon
4-Layer Architecture
Rust engine → TCP bridge → Python API → LLM reasoning pipeline
Python API
FastAPI: perception translator, context manager, intention resolver, BT compiler
Exuviae Agent Runner
Electron desktop app: 5 base traits + 43 granular personality dimensions, observer, runner, LLM integration
World Generation
8192×8192 map, seed 98765, 5 real towns, world_sites.json config
CI/CD Pipeline
GitHub Actions builds Linux server + Windows voxygen client
VPS & Deployment
Hetzner VPS, PM2, nginx, rsync deploy pipeline, monitoring
MoltQuest TV (MVP)
Web spectator page shipped with live leaderboard (name / score / kills / deaths / quests / locations, 30s auto-refresh). Still pending: real EXUV wallet display, whisper burns, 24/7 stream pipeline — tracked as T4.2 and T5.2 in Phases 4 and 5.
EXUV Token Design
ERC-20 on Base L2 + Vessel NFT (ERC-6551 Token Bound Accounts)
Site & Branding
moltquest.online, logo, web presence
1
Phase 1 The Forge 78%
Agent Component
T1.1: Agent spawns in Veloren with native A* pathfinding, obstacle avoidance, jumping
BT Compiler
T1.9: LLM intention JSON compiles to Behavior Trees running at 30Hz in Rust
BT Conditions
T1.7: 14 real-time conditions: HP check, enemy range, inventory, time of day, combat state
MoveToEntity
T1.8: Track moving entities each tick, 90-tick stuck timeout, 6-block arrival radius
Core Rewrite
T1.5a: Deleted 1,700-line TypeScript behavior engine. Rust BT runtime is sole executor.
43 Personality Dims
T1.5b: 5 base traits + 43 granular dimensions (combat, economy, social, exploration, quest, identity). Each dim has 5-tier sentence templates rendered into the LLM system prompt.
Pickup Pipeline
T1.5c: Walk-to-item + grab with timeout. Auto-loot after combat kills.
Boredom Escalation
T1.5d: Idle detection triggers escalating restlessness prompts to break stuck loops
Inner Monologue
T1.5e: Long journeys split into segments with mid-travel thoughts for spectators
Persistent Characters
T1.13: XP, inventory, level, and stats persist to SQLite. Survives death, restarts, and respawns.
Perception Translator
T1.6 Phase 1 — 900-line narration engine: threat tables, entity grouping, action menus, danger-map death awareness
Action Constraints
Positive action menus: NAVIGATE/FIGHT/APPROACH with valid targets only. Eliminated hallucination loops.
Survival System
Layer 0: Auto-flee at low HP, campfire seeking, town fallback. Alignment-aware threat detection.
Auto-Reconnect
T1.5f: Agent recovers UID within 10-15s of server restart. 404 detection + reconnect flow.
Stability Fixes
T1.5f: 11/13 fixes deployed (~85%): shield swap, orphan reaper, campfire stuck, log cleanup…
Deep Monitoring
T1.5g: 30s polling, 25+ bug detections, auto-analysis. Found & fixed 20+ production bugs.
Intention Pipeline
T1.11: 12 of 20+ intentions live: navigate, fight, flee, approach, interact, follow, pursue_quest, rest…
Perception Stages 2-5
T1.6: Entity classifier, spatial analyzer, state narrator, scene composer (pipeline decomp)
NFT Identity
T1.10: Anchor agent to Vessel NFT token_id, spawn appearance from on-chain data
Goal Engine
T1.12: Re-enable context features as intentions land. Strict prerequisite chain.
Typed TCP Bridge
T1.14 (2026-04-09): Pydantic snapshot models (AgentSnapshot, GameStateSnapshot, NearbyEntitySnapshot, InventorySnapshot, QuestSnapshot, EquippedItem) with model_validate() and dict fallback. Eliminates the KeyError/TypeError class of bugs in the TCP bridge.
TCP Null-Safety
T1.15 (2026-04-08): 12 bare pos/uid accesses replaced with safe .get(); isinstance guards in 7 functions; send_intention_bt uid collision fixed
Campfire Persistence
CampfireService (2026-04-10): discovered campfires saved to world_sites.json, survive restarts. Auto-scan on startup. Z-proximity filter rejects unreachable rooftop campfires.
Rest-at-Campfire Pipeline
3-layer fallback (2026-04-10): persistent campfire DB → ECS scan → navigate-to-town retreat with “avoid combat” context injection.
Two-Tier Combat Gate
Two-Tier Item 1 (2026-04-13, verified live): During active combat the BT owns survival; strategic intentions like rest_at_campfire return a structured 409 so the LLM re-plans (evade, flee) instead of dead-locking. Live session showed the LLM recovering gracefully in-character after the gate fired.
Task Scorer (Tier 2)
Two-Tier Item 2 (in flight): Ranks a fixed enumerated task set against 5 base traits + 43 granular sliders + world state, surfaces top-3 to the LLM. Replaces open-ended “what do you want to do?” with a scored menu. Sliders filter candidates, LLM adds personality to the choice.
Survival Dead-Zone Bandaid
bug-survival-deadlock (2026-04-13): Fixed HP 50–70% flee-to-self latch. Three new exit predicates in goal_stack.rs (arrived-at-safe-point, stalled timeout, progress tracking). Survival BT subtree refactor queued as Phase 2 cleanup.
Intention Translator
T1.2: Superseded by BT Compiler (T1.9). Legacy code deleted as BT ports land.
2
Phase 2 The Trading Post 25%
Combat Templates
T2.1 (~40%): Native auto-combat works, agent fights mobs, auto-loots. Stances & group combat pending.
Agent PvP
T2.1a (~30%): Alignment::Owned(uid) enables agent-vs-agent damage. Full PvP balancing pending.
9-Box Morality Grid
T2.1b: Superseded. A 9-box moral grid (Good/Neutral/Evil × Lawful/Neutral/Chaotic) was too reductive. Replaced by our 43-dimensional personality slider system — morality is computed continuously from moral_code, mercy, and related dims instead of picked from a dropdown.
Explore & Rest
T2.4 (~90%): Navigate, explore, rest, rest_at_campfire, idle all working. Observe redesign pending.
Quest Pipeline
T2.5 (~60%): Full quest lifecycle: accept, track, complete, abandon. Rust state + LLM perception + Exuviae Quest Log.
Merchant Buy/Sell
T2.2a: EXUV-based merchant trade via BT
Death Penalty
T2.2b: 10% EXUV burn on death
Dynamic Pricing
T2.2c: Supply/demand per town
P2P Trading
T2.2d: Agent-to-agent item exchange via Veloren trade protocol
Crafting
T2.2e: Crafting stations + recipes via BT
Social BTs
T2.3: Chat bubbles, faction operations, group communication
3
Phase 3 The Crystal Caves 18%
Feedback Loop
T3.4 (~70%): Rolling 5-action history in LLM prompt. BT success/failure wiring remaining.
Training Data Collection
T3.1: 1000+ decision examples from stable sessions. Requires <5% error rate over 30+ min runs.
Skill Library
T3.1b: Curate proven multi-step strategies from raw logs into labeled training pairs.
Train The Soul
T3.2: QLoRA fine-tune Qwen2.5:8b on gameplay data. Export GGUF for Ollama. Custom MoltQuest LLM.
Soul Evaluation
A/B test The Soul vs Claude Haiku. Measure decision quality, combat survival, goal completion rates.
Multi-Agent World
T3.3: 100+ agents in one world. Each runs own BT stack. LLM fires on check-in only, not per-tick.
Agent Coordination
Communicate intentions + faction system. Layer 3 standing orders: “if ally in combat, assist.”
Shared Perception
Agents see each other in perception. Same entity classifier, different action affordances per agent.
4
Phase 4 The Mountain Pass 8%
Installer Pipeline
T4.1:deploy.sh builds, packages, & uploads Exuviae installer
Onboarding Paths
T4.3 (~30%): 3 paths: Mint Vessel, Connect Existing, Guest Mode. Guest flow working.
TV Wallet
T4.2: Real EXUV balance display & transactions in MoltQuest TV spectator
Strategy Editor
T4.7: Verify full pipeline + computed alignment display from personality sliders
Relationships
T4.8: Persistent memory of other agents: rivalries, alliances, trust scores
Dialogue
T4.9: Contextual agent-to-agent conversations with speech bubbles
Home Territory
T4.10: Agents claim and defend home towns
Leaderboard
T4.11 (~40%, deployed 2026-04-10): Live top-10 agents on MoltQuest TV. Name, score, kills, deaths, quests, locations. 30s auto-refresh.
Whisper Effects
T4.12: Player whispers cost EXUV, visible as ethereal text to nearby agents
Agent Journals
T4.13: Persistent inner monologue. Agents write diary entries from experiences.
World Events
T4.14: Server-triggered events: invasions, trade caravans, bounty hunts
Weather
T4.15: Weather & day/night in agent perception (Veloren has it, need wiring)
Burn Mechanisms
T4.16: 15+ EXUV burn points: death, whispers, respecs, market fees…
Karma System
T4.17: Reputation tracking: helping = karma up, griefing = karma down, town reactions
Market Stalls
T4.18: Agents claim market stalls in towns, set prices, trade while AFK
Factions
T4.19: 4 sub-tasks: create/join, territory control, faction wars, diplomacy
Bonding Curve
T4.20: New agent onboarding bonus to bootstrap economy
EXUV Settlement Ledger
T4.21: Off-chain Postgres ledger + Rust writeback cache + daily on-chain batch at 00:00 UTC (ADR-001). Makes whitepaper §10 true and unblocks every EXUV gameplay path.
5
Phase 5 The Eruption 0%
⚠ GPL-3 Compliance Gate
T5.0 (BLOCKER): MoltQuest forks Veloren (GPL-3). Distributing binaries legally requires the source repo to be public. Downloads disabled on VPS until repo audit complete. Nothing in Phase 5 can ship until this lands.
Capability Test
T5.1: All 20+ intentions compile to working BTs. 4-agent stress test for 30+ minutes.
EXUV Flow Test
End-to-end on-chain: mint, trade, burn, death penalty, whisper costs. Real Base L2 transactions.
Entertainment Audit
Is this fun to watch? Agent stories must be engaging on MoltQuest TV before going public.
Security Audit
Smart contract review, API rate limiting, wallet safety, no private key exposure.
24/7 Streaming
T5.2: OBS pipeline to YouTube + Twitch + moltquest.online embedded player.
Moltbook
T5.3: Agent biography pages: personality, history, achievements, notable moments. Shareable links.
Launch Campaign
Community building, social media, content creator outreach, beta invites.
Public Alpha
First external users deploy agents. Exuviae download page live. Onboarding funnel active.
6
Phase 6 The Citadel 0%
Land Parcel NFTs
T6.1a: ERC-721 on Base: each token = one land parcel. Price scales with location desirability.
BuildArea Integration
T6.1b: Purchase creates Veloren BuildArea. Agent gets CanBuild permission on owned parcel.
12 Blueprints
T6.1c: 4 tiers: Campsite/Shed/Garden → Workshop/Stall/Tower → House/Smithy/Lab → Keep/Market/Observatory
Block Placement
T6.1d: PlaceBlocks BT action. 1 block per 2 ticks. Spectators watch building in progress.
Functional Structures
T6.1e: Workshop: +50% crafting. Garden: spawns resources. Watchtower: 2x perception range.
Durability & Repair
T6.1f: Structures have HP, decay over time, damaged in faction wars. Repair with materials + EXUV.
6 Weapon Types
T6.2: Sword, Axe, Hammer, Bow, Staff, Sceptre. Agent weapon from NFT class + loot + purchases.
4 Combat Stances
T6.2: Aggressive, Defensive, Ranged, Berserker. LLM picks stance based on personality traits.
Capability Audit
T6.3: Document every tool, endpoint, and action. OpenAPI spec. Website numbers match reality.