Skip to content
View Aagam-Bothara's full-sized avatar
🤔
Thinking
🤔
Thinking

Block or report Aagam-Bothara

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. rigtune rigtune Public

    Measures which LLM serving settings pay off on your GPU and your traffic, then serves the winner. Benchmarks vLLM, SGLang and llama.cpp configurations; one OpenAI-compatible AP

    Python 12 1

  2. llmtrace llmtrace Public

    A Python library to find out why vLLM requests are slow, trace latency and GPU energy, and test which configuration changes actually help.

    Python 2

  3. Joule Joule Public

    Joule is an execution runtime for AI agents that does not trust an agent just because it says “I’m done.” It verifies the work externally and only spends additional agents when the current result i…

    TypeScript

  4. iwc-core iwc-core Public

    Python 2

  5. rag-reliability-engine rag-reliability-engine Public

    Retrieval-Augmented Generation (RAG) system with hybrid search (FAISS + BM25), cross-encoder reranking, and confidence-aware answer verification. Detects retrieval failures, performs multi-hop quer…

    Python

  6. CASE CASE Public

    Python