laconiq-ai

laconiq-ai/tekmyra

Context compression for LLM pipelines that proves nothing protected was lost before it emits, and refuses when it cannot. Refusals count against the published numbers. Paper, benchmarks and receipts ship with the code. Open core by LaconIQ. Apache-2.0.

4 good first / help-wanted issues · Python · last activity Sep 1, 2026

3 stars 0 forks 3 watchers Python Apache License 2.0
apache-2-0 compression context-compression llm machine-learning prompt-compression prompt-engineering python rag
4 Open Issues Need Help Last updated: Sep 1, 2026

Open Issues Need Help

View All on GitHub
laconiq-ai/tekmyra
3

Context compression for LLM pipelines that proves nothing protected was lost before it emits, and refuses when it cannot. Refusals count against the published numbers. Paper, benchmarks and receipts ship with the code. Open core by LaconIQ. Apache-2.0.

Python
#apache-2-0#compression#context-compression#llm#machine-learning#prompt-compression#prompt-engineering#python#rag
laconiq-ai/tekmyra
3

Context compression for LLM pipelines that proves nothing protected was lost before it emits, and refuses when it cannot. Refusals count against the published numbers. Paper, benchmarks and receipts ship with the code. Open core by LaconIQ. Apache-2.0.

Python
#apache-2-0#compression#context-compression#llm#machine-learning#prompt-compression#prompt-engineering#python#rag
laconiq-ai/tekmyra
3

Context compression for LLM pipelines that proves nothing protected was lost before it emits, and refuses when it cannot. Refusals count against the published numbers. Paper, benchmarks and receipts ship with the code. Open core by LaconIQ. Apache-2.0.

Python
#apache-2-0#compression#context-compression#llm#machine-learning#prompt-compression#prompt-engineering#python#rag
laconiq-ai/tekmyra
3

Context compression for LLM pipelines that proves nothing protected was lost before it emits, and refuses when it cannot. Refusals count against the published numbers. Paper, benchmarks and receipts ship with the code. Open core by LaconIQ. Apache-2.0.

Python
#apache-2-0#compression#context-compression#llm#machine-learning#prompt-compression#prompt-engineering#python#rag