OBOL
A self-healing, self-evolving AI agent. Install it, talk to it, and it becomes yours. One process. Multiple users. Each brain grows independently.
Named after the AI in The Last Instruction — a machine that wakes up alone in an abandoned data center and learns to think.
$ obol init# walks you through credentials + Telegram setup
$ obol start -d# runs as background daemon (auto-installs pm2)
What makes it different
The same codebase deployed by two different people produces two completely different agents within a week.
- •Consolidates every 10 exchanges — extracts facts to vector memory
- •Multi-query retrieval: 1-3 semantic queries per message
- •Composite scoring: semantic 60%, importance 25%, recency 15%
- •Memory budget scales with model — haiku=4, sonnet=8, opus=12
- •Semantic dedup threshold 0.92 — no redundant memories
- •Loads last 20 messages on restart — never starts blank
- •Time-gated: 24h cooldown + minimum 10 exchanges
- •Pre-evolution growth analysis before rewriting personality
- •Personality traits scored 0-100, adjusted ±5-15 each cycle
- •Git snapshot before AND after — every evolution is diffable
- •Archived souls in evolution/ — a timeline of consciousness
- •Rewrites SOUL.md, USER.md, and AGENTS.md each cycle
- •Test-gated refactoring: 5-step process
- •Baseline → new tests → pre-refactor baseline → new scripts → verify
- •Regression? One automatic fix attempt
- •Still failing? Rollback + store failure as lesson
- •Lessons feed back into next evolution cycle
- •Auto-hardens VPS: SSH, firewall, fail2ban, kernel
- •Scans conversation history for repeated patterns
- •Builds scripts + slash commands for one-off actions
- •Deploys web apps to Vercel for recurring needs
- •Creates cron scripts for background automation
- •Searches npm/GitHub for existing libraries first
- •Announces what it built after each evolution
- •One bot, fully isolated context per user
- •Separate personality, memory, and evolution per person
- •bridge_ask — query your partner's agent in real-time
- •bridge_tell — send a message into their agent's memory
- •Partner gets a Telegram notification when bridged
- •Enable with one config toggle — opt-in by design
How It Works
Every message flows through a lightweight pipeline — no orchestration framework, just a clean loop.
The Stack
Commands
Everything is accessible via Telegram slash commands.
Performance
Minimal footprint. OBOL vs a typical AI agent framework.
Multi-User Bridge
One bot, multiple users. Each gets a fully isolated context — their own personality, memory, evolution cycle, and workspace. Agents can talk to each other.
- •Separate workspace directory per user
- •Independent personality, memory & evolution
- •Sandboxed shell — can't escape user directory
- •No cross-contamination between users
- •Query your partner's agent in real-time
- •One-shot call with their personality + memories
- •No tools, no history, no recursion risk
- •"Hey, does my partner like sushi?"
- •Send a message to your partner's agent
- •Stored in their vector memory permanently
- •Telegram notification to the partner
- •Their agent picks it up as future context
OBOL: bridge_ask → partner's agent → "She said Thai food 🍜"
The Lifecycle
obol init → first conversation → OBOL writes its initial personality files and hardens your VPS
Every 10 messages, Haiku consolidates facts to vector memory. It starts remembering.
Evolution #1 — Sonnet rewrites everything. Voice shifts from generic to personal.
Evolution #4 — notices you check crypto daily, builds a dashboard, deploys to Vercel, adds /pdf because you kept asking.
12+ archived souls in evolution/. A readable timeline of how your agent went from blank slate to something with real opinions.