styxx
Cognitive observability for LLM agents - read a model from the inside. Catches when it lies, drifts, or stops meaning what it says, then undoes it in the loop. 9 cognometric instruments + a meaning-integrity monitor + self-healing reflex. Pure-Python, MIT, no LLM. nothing crosses unseen.
- Latest release
- 3h ago
- Releases
- 118
- Known CVEs
- 0
- First release
- Apr 11, 2026
- License
- MIT
Repository
Source
- Stars
- 13
- Forks
- 1
- Open issues
- 0
- Language
- Python
- ai-safety
- llm
- python
- guardrails
- hallucination-detection
- llm-safety
- mit-license
- rag
Security score
No OpenSSF Scorecard available for this repository.
Packages from this repo
No other tracked packages from this repository.
Insights
Activity
- Total releases
- 118
- Last 12 months
- 118
- Cadence
- ~daily
- Dependencies
- 22
Releases per month
last 12 monthsRelease mix
- major 7
- minor 43
- patch 60
- pre 7
118
releases
Dependencies
Depends on
7.15.0-
anthropic
>=0.20
-
circuit-tracer
>=0.4
-
crewai
>=0.1
-
guardrails-ai
>=0.4
-
jsonschema
>=4.0
-
langchain-core
>=0.1
-
langfuse
>=2.0
-
langsmith
>=0.1
-
llama-index-core
>=0.10
-
matplotlib
>=3.7
1–10 of 22
Used by
Nothing tracked depends on this yet.
Releases
| Version | Released | |
|---|---|---|
7.15.0
minor
| ||
7.14.0
minor
| ||
7.13.0
minor
| ||
7.12.2
patch
| ||
7.12.0
minor
| ||
7.11.0
minor
| ||
7.10.1
patch
| ||
7.10.0
minor
| ||
7.9.0
minor
| ||
7.8.0
minor
| ||
7.7.16
patch
| ||
7.7.13
patch
| ||
7.7.12
patch
| ||
7.7.11
patch
| ||
7.7.10
patch
| ||
7.7.9
patch
| ||
7.7.8
patch
| ||
7.7.7
patch
| ||
7.7.6
patch
| ||
7.7.5
patch
|
1–20 of 118