LoRA fine-tune Gemma 4 31B to speak caveman-mode natively. Style: github.com/JuliusBrussee/caveman
-
Updated
May 17, 2026 - Python
#
caveman
Here are 13 public repositories matching this topic...
OpenCode package for Caveman: terse AI responses, slash commands, compact reviews, commit messages, and markdown memory compression.
-
Updated
Jun 18, 2026 - Python
Caveman prompting, measured. A two-channel evaluation protocol scoring what input and output compression actually cost LLMs in dollars, accuracy, and surface-text fidelity across seven models and five benchmarks.
nlp benchmark openai token reproducibility evaluation-framework caveman large-language-models prompt-engineering anthropic llm-evaluation prompt-compression inference-cost
-
Updated
Jun 26, 2026 - Python
🪨 Cut LLM token costs 40-75%. Works with Claude Code, Gemini CLI, Codex, aider. No API key needed.
python ai pyspark gemini caveman llm cost-reduction prompt-compression claude-code token-optimization
-
Updated
May 20, 2026 - Python
Terse, token-efficient communication skill for Kimi Code CLI. Cut 60-75% of output tokens while keeping full technical accuracy.
-
Updated
May 4, 2026 - Python
Caveman mode for pi: ultra-compressed agent responses, terse commits, reviews, and memory compression.
-
Updated
Apr 29, 2026 - Python
Caveman-compressed reasoning trace curator for token-efficient SFT datasets
-
Updated
May 13, 2026 - Python
Make caveman worse by giving it Claptrap personality. Same 75% token savings. Personality more annoying. 🤖
-
Updated
Apr 13, 2026 - Python
Caveman terse communication mode for Pi and Codex
-
Updated
May 2, 2026 - Python
Reduce LLM token usage by 40–75 percent with this CLI tool and SDK. Optimize prompts for Claude, OpenAI, and other models without needing an API key.
python productivity open-source ai pyspark gemini developer-tools caveman llm cost-reduction prompt-compression claude-code token-optimization token-optimizer
-
Updated
Jul 1, 2026 - Python
Save tokens with persistent code memory and structural navigation for Claude Code
java workflow deployment tumblr generate blockchain transformers tokens intellij-plugin document sso token bert springcloud aouth2 caveman rpa token-list anthropic claude-code
-
Updated
Jul 1, 2026 - Python
MCP server tools for Claude-Desktop app, for reducing token consumption, the input tokens are reduced by MCP server tools and the output tokens are reduced by Caveman skill
-
Updated
Apr 17, 2026 - Python
Improve this page
Add a description, image, and links to the caveman topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the caveman topic, visit your repo's landing page and select "manage topics."