akiva ai
Popular repositories Loading
-
enterprise-crypto
enterprise-crypto PublicOpen-source multi-agent crypto trading system with institutional-grade risk controls, multi-exchange support, and autonomous strategy execution.
TypeScript 1
-
toolkit-llm-gateway
toolkit-llm-gateway PublicEnterprise LLM proxy with unified multi-provider API, cost attribution, rate limiting, caching, and analytics -- based on LiteLLM.
Python 1
-
toolkit-eval-harness
toolkit-eval-harness PublicAI/ML evaluation harness -- versioned golden test suites, deterministic scoring, regression detection, and CI/CD-integrated reporting.
Python 1
-
toolkit-policy-test-bench
toolkit-policy-test-bench PublicRed-team and compliance test harness for LLM outputs -- detects PII leakage, secret exposure, and policy violations with CI-friendly reporting.
Python 1
-
toolkit-rag-quality
toolkit-rag-quality PublicDeterministic RAG evaluation toolkit -- retrieval metrics (recall, precision, MRR), corpus overlap detection, and CI regression gating without model calls.
Python 1
-
toolkit-cost-optimizer
toolkit-cost-optimizer PublicLLM inference cost and latency optimizer -- log analysis, SLO-based model recommendations, and routing policy simulation.
Python 1
Repositories
- enterprise-crypto Public
Open-source multi-agent crypto trading system with institutional-grade risk controls, multi-exchange support, and autonomous strategy execution.
AKIVA-AI/enterprise-crypto’s past year of commit activity - toolkit-mmqa Public
Multimodal dataset QA -- directory scanning, file hashing, and exact duplicate detection for text, image, and audio datasets.
AKIVA-AI/toolkit-mmqa’s past year of commit activity - toolkit-cost-optimizer Public
LLM inference cost and latency optimizer -- log analysis, SLO-based model recommendations, and routing policy simulation.
AKIVA-AI/toolkit-cost-optimizer’s past year of commit activity - toolkit-rag-quality Public
Deterministic RAG evaluation toolkit -- retrieval metrics (recall, precision, MRR), corpus overlap detection, and CI regression gating without model calls.
AKIVA-AI/toolkit-rag-quality’s past year of commit activity - toolkit-inference-mesh Public
Distributed LLM inference mesh for heterogeneous clusters -- pipeline-parallel sharding with SGLang, MLX-LM, and P2P networking. Fork of Parallax.
AKIVA-AI/toolkit-inference-mesh’s past year of commit activity - toolkit-ml-provenance Public
ML provenance and SBOM generator -- deterministic manifests with integrity verification and optional cryptographic signing for datasets, configs, code, and model weights.
AKIVA-AI/toolkit-ml-provenance’s past year of commit activity - toolkit-llm-gateway Public
Enterprise LLM proxy with unified multi-provider API, cost attribution, rate limiting, caching, and analytics -- based on LiteLLM.
AKIVA-AI/toolkit-llm-gateway’s past year of commit activity - toolkit-data-contracts Public
Data contract management and drift detection for ML/LLM pipelines -- automatic schema inference, validation, and statistical profiling with CI/CD integration.
AKIVA-AI/toolkit-data-contracts’s past year of commit activity - toolkit-eval-harness Public
AI/ML evaluation harness -- versioned golden test suites, deterministic scoring, regression detection, and CI/CD-integrated reporting.
AKIVA-AI/toolkit-eval-harness’s past year of commit activity - toolkit-policy-test-bench Public
Red-team and compliance test harness for LLM outputs -- detects PII leakage, secret exposure, and policy violations with CI-friendly reporting.
AKIVA-AI/toolkit-policy-test-bench’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…