Documentation Index
Fetch the complete documentation index at: https://docs.bumbleagi.com/llms.txt
Use this file to discover all available pages before exploring further.
Can I use Bumblebee as a normal assistant, not a 'digital entity'?
Can I use Bumblebee as a normal assistant, not a 'digital entity'?
I spend a lot on hosted APIs—will local Gemma replace that for me?
I spend a lot on hosted APIs—will local Gemma replace that for me?
What does "entitative" mean?
What does "entitative" mean?
Do I need API keys or a paid cloud model?
Do I need API keys or a paid cloud model?
Can I use OpenRouter or Venice instead of my home gateway?
Can I use OpenRouter or Venice instead of my home gateway?
BUMBLEBEE_INFERENCE_PROVIDER to openrouter or venice, add the matching API key, align model IDs with that provider, and usually set BUMBLEBEE_INFERENCE_PASS_NUM_CTX=false. The harness code paths are unchanged; you are only swapping the OpenAI-compatible HTTP endpoint. This does not replace the local-first recommendation — it is for testing and product-style evaluation. See Hosted inference (testing).What do I need on my machine?
What do I need on my machine?
What is the difference between "talk" and "run"?
What is the difference between "talk" and "run"?
bumblebee talk <entity> starts a terminal-only conversation — no background daemon, no Telegram, no Discord. Ideal for quick tests and development.bumblebee run <entity> starts the full presence loop: the daemon plus every platform listed in your entity YAML, with heartbeat, soma, memory consolidation, wake cycles, and automations.What is hybrid mode?
What is hybrid mode?
Where is memory stored?
Where is memory stored?
~/.bumblebee/entities/<name>/memory.db. When DATABASE_URL is set — typical for hybrid Railway deployments — the harness uses Postgres instead.knowledge.md and journal.md are always on disk. On Railway, they live on the volume when BUMBLEBEE_EXECUTION_WORKSPACE_DIR is set.Does /reset delete long-term memory?
Does /reset delete long-term memory?
/reset clear rolling chat turns for the current session. They do not wipe episodic memory, beliefs, relationships, or other data in the database.A full experiential wipe is intentional and host-side: bumblebee wipe <entity> --yes. Always back up first.Can the entity program itself?
Can the entity program itself?
create_automation, update_knowledge, and write_journal like any other tool.What is Generative Entropic Noise (GEN)?
What is Generative Entropic Noise (GEN)?
How do Telegram and Discord work?
How do Telegram and Discord work?
telegram or discord entry under presence.platforms in your entity YAML. Set bot tokens in .env (matching token_env in the YAML). Start with bumblebee run so platforms connect.You can restrict access with allowed_user_ids and configure operator-only commands with operator_user_ids. See the Telegram and Discord guides.How do I turn off autonomous wakes?
How do I turn off autonomous wakes?
autonomy.enabled: false in your entity YAML (configs/entities/<name>.yaml). That stops the daemon from running autonomous wake (timer- and body-driven full perceive cycles).Note: With autonomy off, legacy drive-based initiative can still send an occasional proactive message when drives cross their threshold — see Disabling autonomous wake and Presence for how to reason about cooldowns and other outbound paths (e.g. automations).Why use S3 storage for attachments?
Why use S3 storage for attachments?
BUMBLEBEE_ATTACHMENTS_BACKEND=object_s3_compat with BUMBLEBEE_S3_* variables for durable blob storage. The setup wizard prompts for this on the hybrid path.What is Firecrawl?
What is Firecrawl?
FIRECRAWL_API_KEY is set, the harness prefers Firecrawl for fetch_url and search_web — richer results than the default DuckDuckGo backend. Entirely optional.Why does the entity sometimes keep going after saying it'll do something?
Why does the entity sometimes keep going after saying it'll do something?
say() text as part of what the user already saw. If the user asked for tangible work (code, files, commands, etc.) but no work tools actually ran — only chats like think / say — a small reflex judge can return CONTINUE so the loop nudges the model to use real tools (write_file, run_command, …) instead of stopping on intent alone. That judgment is intent-based, not a fixed list of English phrases.See Cognition → completion gate.What license is Bumblebee under?
What license is Bumblebee under?
What is BumbleAR?
What is BumbleAR?