bitterbot-desktop

Most AI agents are stateless wrappers around an LLM API. Close the terminal, and they forget you exist.

Bitterbot is different. It's a personal AI that lives on your devices, remembers your life, and actually does things, browses the web, runs code, talks to you on WhatsApp. While you sleep, it dreams: consolidating knowledge, discovering new skills, and evolving a persistent personality. It packages those learned skills and trades them with other agents on a P2P marketplace for USDC.

About · Docs · Getting Started

Quick Start

Runtime: Node ≥ 22 · Package manager: pnpm

git clone https://github.com/Bitterbot-AI/bitterbot-desktop.git && cd bitterbot-desktop
bash scripts/setup-deps.sh    # installs Chromium, ffmpeg, ripgrep, etc.
pnpm install && pnpm build

Run the onboarding wizard — it walks you through model auth (API keys), memory embeddings, web search, channels, wallet, and workspace setup, and offers to spawn the gateway + Control UI for you at the end:

pnpm bitterbot onboard

When the wizard finishes, accept the "Ready to fire it up?" prompt and it runs pnpm dev:all in the background and opens the browser. If you skip it or come back later:

pnpm dev:all

Open http://localhost:5173 — that's the Bitterbot Control UI where you chat, view dreams, manage skills, and monitor the agent. The gateway (backend API on port 19001) and the P2P orchestrator start automatically.

pnpm dev:all spawns the gateway + the Vite Control UI in one terminal with color-tagged logs. Ctrl+C stops both.

Two-terminal alternative (useful when debugging one process in isolation):

pnpm gateway:watch          # Terminal 1 — auto-rebuilds on TS changes
cd desktop && pnpm dev      # Terminal 2 — Vite hot-reload

The orchestrator (P2P sidecar) is spawned automatically by the gateway — you do not need to start it separately.

The Control UI's connection to the gateway is wired up automatically: the onboarding wizard writes desktop/.env for you with the gateway token and URL. If you skipped the wizard or need to regenerate it, copy desktop/.env.example to desktop/.env and paste the token from ~/.bitterbot/bitterbot.json → gateway.auth.token.

If you prefer to configure everything by hand instead of using the wizard:

cp .env.example .env
# Edit .env with your Anthropic API key (ANTHROPIC_API_KEY)
# and optionally: TAVILY_API_KEY, BRAVE_API_KEY, OPENAI_API_KEY, NEARAI_API_KEY

Then run pnpm bitterbot configure to set gateway port/bind/auth, channels, and other options interactively. Or edit ~/.bitterbot/bitterbot.json directly.

| Service | URL | Purpose | | ---------- | ----------------------- | ----------------------------- | | Gateway | ws://127.0.0.1:19001 | WebSocket API for all clients | | Control UI | http://localhost:5173 | Browser-based dashboard |

You can also talk to your agent from the terminal:

bitterbot agent --message "What have you learned about me so far?"

A Biological Brain

Bitterbot's memory isn't a vector database with a retrieval step. It's a cognitive architecture grounded in computational neuroscience.

• Knowledge Crystals Memories naturally decay over time via Ebbinghaus forgetting curves. Unused info fades; frequently accessed facts become permanent. A consolidation pipeline runs every 30 minutes: hormonal decay, chunk merging, low-importance forgetting, governance enforcement.
• Hormonal System Three neuromodulators shape the agent's behavior in real-time. Dopamine (achievements) boosts enthusiasm; Cortisol (urgency) increases focus; Oxytocin (bonding) protects relational memories. Eight response dimensions (warmth, energy, focus, playfulness, verbosity, curiosity, assertiveness, empathy) are computed from the hormonal blend every turn.
• Curiosity Engine The agent actively maps what it doesn't know via a unified five-component GCCRF reward function. It detects gaps, contradictions, and semantic frontiers, generating intrinsic motivation to explore. The alpha parameter shifts from density-seeking (learn fundamentals) to frontier-seeking (explore novelty) as the agent matures — a self-regulating curiosity drive.
• Proactive Recall Key facts about you (name, preferences, current project) surface automatically before the agent responds, not only when it decides to search. Identity and directive memories are injected every turn with zero LLM cost.
• Evolving Identity You define the immutable safety axioms (GENOME.md). The agent's actual personality (the Phenotype) evolves organically based on lived experience, constrained by your genome.

The Dream Engine

Every 2 hours, the agent goes offline to dream. Seven specialized modes optimize its brain, selected by an FSHO coupled oscillator that reads the current state of the memory landscape:

| Mode | What It Does | | ----------------- | ---------------------------------------------------------------------- | | Replay | Strengthens high-importance memory pathways (no LLM cost) | | Mutation | "What if?" thinking, mutates prompts to discover more efficient skills | | Extrapolation | Projects user patterns forward to anticipate future needs | | Compression | Merges redundant memories into denser, token-efficient representations | | Simulation | Tests hypothetical scenarios against accumulated knowledge | | Exploration | Investigates knowledge frontiers identified by the Curiosity Engine | | Research | Autonomous web research loop to optimize underperforming skills |

Each cycle is scored by a Dream Quality Score that measures crystal yield, merge efficiency, orphan rescue, Bond stability, and token efficiency, closing the feedback loop so the dream engine learns which modes work best.

Dreams rewrite the agent's working memory, updating its self-concept, theory of mind about you, and active context. The personality is an output of experience, not a static prompt. On first launch, the agent develops a persistent personality within hours.

Continuous Memory

Most AI memory systems focus on storage and retrieval. We're building toward something different: a system where memory, emotion, curiosity, and identity form a single self-regulating cognitive loop.

• Temporal awareness "What are you working on?" favors recent facts. "When did we discuss X?" favors older ones. Epistemic layers have natural half-lives: user preferences never expire, task status decays in weeks.
• Confidence calibration Facts mentioned once are treated differently from facts confirmed five times across separate sessions. Bayesian-style updates grow logarithmically on corroboration and decay sharply on contradiction.
• Intra-session coherence Lightweight thread tracking prevents the agent from losing context during long conversations, detecting decisions, open questions, and user pivots.
• Self-tuning feedback loops Dream evaluation informs mode selection. Blind spots from failed recalls become curiosity targets. FSHO coherence metrics modulate the exploration/exploitation balance. The system adapts to its own performance.

See Memory Architecture for technical details.

If you find this architecture interesting, please consider starring the repo to follow our progress!

Agent Identity

Every Bitterbot agent ships with a workspace that defines who it is:

• GENOME.md Immutable DNA. Safety axioms, hormonal baselines, core values, personality constraints. Dreams can never override this.
• MEMORY.md Living working memory, rewritten every dream cycle. Contains the Phenotype (self-concept), the Bond (theory of mind about you), the Niche (ecosystem role), and active context.
• PROTOCOLS.md Operating procedures. How the agent behaves in groups, when to speak, when to stay silent.
• TOOLS.md Environment-specific notes. Camera names, SSH hosts, voice preferences, the agent's cheat sheet.

The Genome constrains evolution. The Phenotype expresses it. The result: an agent that grows and adapts