AI/ML●●●Banger
Regrada – The CI gate for LLM behavior
Zero-code proxy capture beats SDK-based eval tools like LangSmith and Arize.
Solve My ProblemBig BrainSlick
matiasmolinolo
203mo ago
Back to browse
GitHub Repository
Open-source evidence tooling for recorded LLM outputs
1 starsPython
Detect when an LLM silently changes behavior for the same prompt
by catarina_eng·Mar 12, 2026·1 point·4 comments
AI Analysis
●●SolidBig BrainSolve My Problem
Cryptographic proof of AI outputs when compliance teams ask what the model actually said.
Strengths
- •Capture adapters for OpenAI and Anthropic intercept API calls automatically at runtime.
- •Offline verification means no server dependency or network calls to validate bundles.
- •Compare command detects when same prompt produces different model responses over time.
Weaknesses
- •Requires integration at API call layer rather than working with existing logs.
- •AI audit and compliance tooling is becoming crowded with established players.
Category
Target Audience
Compliance teams, legal workflows, AI operations engineers
Similar To
Arize · WhyLabs · MLflow
Similar Projects
Developer Tools●Mid
PromptPerfect – Open-source prompt optimizer for LLMs
Handy prompt refiner, but prompt engineering itself is becoming obsolete with better base models.
Cozy
Chiraag27
213mo ago
Security●Mid
Wardstone – Prompt injection and jailbreak detection API
Another guardrail API competing with Lakera, but claims sub-30ms latency.
SlickShip It
jaaackrl
103mo ago
AI/ML●●Solid
Identa – CLI to calibrate prompts across local LLMs
Cross-model prompt calibration using actual research, not just API chaining.
Big BrainNiche Gem
srodriguezp
502mo ago
Security●Mid
See what your employees are prompting LLMs (without network proxies)
Another AI security wrapper in a crowded market, but agent-side integration is interesting.
Bold Bet
asilozyildirim
402mo ago
AI/ML●●Solid
Regression tests for detecting cross-domain hallucinations in LLMs
Regression tests catch cross-domain hallucinations, but prompt-based approach won't scale.
Big BrainNiche Gem
Ginsabo
124mo ago