curiosity-loop skillA
curiosity-loop is agent-read markdown (skill) from bitterbot-ai/bitterbot-desktop: Use when the user asks what you are curious about or do not know, wants dream-synthesized insights, or after you investigate an exploration target. Not for plain fact recall (use memory_search)..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Curiosity loop ## Curiosity engine The curiosity engine tracks knowledge gaps, anomalies, frontiers and contradictions. Each new chunk is assessed for novelty and surprise. Exploration targets are generated for areas where your knowledge is thin or stale, and the engine rebuilds its knowledge regions during every consolidation pass. Many open gaps bias the dream engine toward exploration mode. ## Tools - `curiosity_state`: view knowledge gaps, exploration targets, learning progress and surprise assessments. Reach for it when the user asks "what do you know about X?", "what are you curious about?" or "what don't you know?". - `curiosity_resolve`: mark an exploration target as resolved after investigating it. Close targets you actually resolved; do not close them to tidy the list. - `dream_search`: search cross-domain insights synthesized during dream cycles. Use it when you want creative connections across topics. - `dream_status`: dream engine state, last cycle details, insight count. ## MEMORY.md sections that feed the loop - **Curiosity Gaps**: what you want to explore next (rewritten by the dream engine). …
Read the whole file at its exact version.
How to install
mdr add bitterbot-ai/bitterbot-desktop/curiosity-loop@git:20260920.a205fe6mdr add bitterbot-ai/bitterbot-desktop/curiosity-loop@sha256:fa56110397328886Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_fglhln5p6b4iidmh)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (1680 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
bitterbot-ai/bitterbot-desktop · 2,460 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fglhln5p6b4iidmh GET https://markdownregistry.com/api/v1/resolve?ref=bitterbot-ai/bitterbot-desktop/curiosity-loop GET https://markdownregistry.com/api/v1/blob/fa561103973288868f0cf286f08ed934c0ab99b567b1086b580f6312a1b4dc24
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.