doofzoff / SIMURG
Zero-leak online detection of LLM decoding corruption and Free Web Search for your AI agents! Catch repetition loops, language drift and garbage mid-stream, before the user sees a bad token. Works with any OpenAI-compatible API.
Why this job: says: openai compatible; topics: openai-api
What it does
Catch LLM decoding corruption while the answer is still being generated and cut the stream mid-flight: corruption that starts in the hold window never reaches the user, and mid-stream corruption is aborted within a few hundred characters of onset, so the host regenerates the answer.
Get started
pip install simurg
# numpy only
pip install simurg[figures]
# + matplotlib, for the paper plots
pip install simurg[test]
# + pytest- Maintenance
- Active
- Last commit 49 days ago
- Stars
- 104
- +1 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.0.4
- Released 49 days ago
- Built with
- Python
- 81% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 1 merged
- 0 waiting
- Releases
- 5
- 5 in the last year
- No contributing guide
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- Python 81%
- HTML 19%
Topics
- anomaly-detection
- guardrails
- hallucination-detection
- inference
- llm
- llm-safety
- online-learning
- openai-api
- streaming
- vllm
Project record
- JobModel gateways
- StatusListed
- Commits34
- Forks15
- Watching3
- Stars in 28 days+8
- CreatedJul 20, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026