open-collider

A semantic collision engine for non-trivial LLM idea generation. Operationalizes Koestler's bisociation theory (1964): injects structurally distant knowledge domains into the prompt, forces collisions, surfaces non-trivial ideas. Empirical validation in CL-ML/open-collider-research.

CL-ML/open-collider

View on GitHub ↗

A semantic collision engine for non-trivial LLM idea generation. Operationalizes Koestler's bisociation theory (1964): injects structurally distant knowledge domains into the prompt, forces collisions, surfaces non-trivial ideas. Empirical validation in CL-ML/open-collider-research.

open-collider grew +0.9% in the last 30 days, ranks 519th of 1,105 in Prompting & Scaffolding, last commit 189 days ago.

Star trajectory

82 days tracked
2026-08-31347 stars today2026-11-22
Momentum

+0.9% in 30d, below the Prompting & Scaffolding median of +1.5%.

Maintenance

Last commit 189 days ago, staler than the median of 35d.

How it compares in Prompting & Scaffolding

open-collider
347
stars
+0.9% 30d
commit 189 days ago
Prompting & Scaffolding median
319
stars
+1.5% 30d
commit ~35d ago
Leader · ponytail
196.6k
stars
+13.0% 30d
commit today

Ranked 519th of 1,105 by stars.

Ranked by shared tags, then keywords, then stars
  1. OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

    +80 (+1.1%) in 30d · Committed yesterday · Python · Apache-2.0

    Shares Prompting & Scaffolding, Memory & Knowledge (RAG)

  2. Inference-native Tokenmaxxing Agent Harness for Loop Engineering

    +4 (+0.7%) in 30d · Committed 156d ago · TypeScript · Apache-2.0

    Shares Prompting & Scaffolding, Memory & Knowledge (RAG)

  3. 利用claude code agent框架一步一步实现deep research!很强大很简单的skills。我一步一步介绍实现deep research,因为deep…

    +0 (+0.0%) in 30d · Committed 327d ago

    Shares Prompting & Scaffolding, Memory & Knowledge (RAG)

  4. 基于原生 Spring AI 的智能体(Agent)开发框架,提供 ReAct 执行引擎、分层记忆、工具调度、Human-in-the-Loop 等核心能力,形成完整的 Harness Engineering…

    +11 (+5.3%) in 30d · Committed 9d ago · Java · Apache-2.0

    Shares Prompting & Scaffolding, Memory & Knowledge (RAG)

  5. Official code for NeurIPS2025 "Iterative Self-Incentivization Empowers Large Language Models as Agentic…

    -3 (-1.4%) in 30d · Committed 311d ago · Python · Apache-2.0

    Shares Memory & Knowledge (RAG), Prompting & Scaffolding

  6. Claude skill & plugin: turn Claude (or any LLM) into an MBB-grade management consultant. Case-interview…

    +24 (+17%) in 30d · Committed 61d ago · HTML · Other license

    Shares Prompting & Scaffolding, Memory & Knowledge (RAG)

  7. SparseRead: token-efficient reading for AI agents. 读得更少,token 更省,证据不变。 Paper arXiv:2608.22237

    -84 (-35%) in 30d · Committed 10d ago · Python · MIT

    Shares Prompting & Scaffolding, Memory & Knowledge (RAG)

  8. [EACL'26] DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router

    +0 (+0.0%) in 30d · Committed 321d ago · Python

    Shares Memory & Knowledge (RAG), Prompting & Scaffolding

  9. Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding…

    +2.7k (+3.5%) in 30d · Committed today · Python · Apache-2.0

    Shares Prompting & Scaffolding, Memory & Knowledge (RAG)

  10. 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI…

    +839 (+1.1%) in 30d · Committed 255d ago · MDX · MIT

    Shares Memory & Knowledge (RAG), Prompting & Scaffolding

Language
Python
License
MIT License
Contributors
1
Forks
35
Watchers
1
Open issues
0
Releases
0
Created
2026-05-10
Stars this week
+0

You've seen where open-collider stands today.

Get the moves before everyone else: the 5 Prompting & Scaffolding repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain open-collider?

Claim this page to add your own call-to-action.

Claim this page