Skip to content
View shashwat134's full-sized avatar
  • TechChefz Digital
  • Jaipur, India
  • 13:34 (UTC +05:30)

Block or report shashwat134

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. agent-from-scratch agent-from-scratch Public

    A minimalist implementation of AI agents (Plan-and-Execute & ReAct) using raw Python and direct API calls. No frameworks, no magic—just first principles. Supports OpenAI, Anthropic, and Gemini.

    Python

  2. AI-Knowledge-Crawler-Local-Vector-Engine AI-Knowledge-Crawler-Local-Vector-Engine Public

    A blazing-fast, concurrent web scraping platform built on FastAPI and Crawl4AI. Features dynamic JS rendering, session handling, authenticated crawling workflows, and a fully offline local AI vecto…

    Python

  3. coding-agent-tracing coding-agent-tracing Public

    One observability layer across coding agents — normalize Claude Code, Codex, dcode & more into a shared LangSmith trace schema to reconstruct, debug, and eval agent sessions.

    Python

  4. multi-model-coding-agent multi-model-coding-agent Public

    A lightweight, multi-model (Gemini, Claude, GPT) autonomous AI coding assistant that natively reads, writes, and executes Python code inside secure local workspaces.

    Python

  5. quantized-semantic-search quantized-semantic-search Public

    Search millions of documents in under 200ms on CPU using a multi-stage retrieval pipeline: binary embeddings for fast recall, int8 embeddings for accurate rescoring, and float32 embeddings for prec…

    Python

  6. zero-waste-agentic-rag zero-waste-agentic-rag Public

    A cost-aware, agentic Retrieval-Augmented Generation (RAG) platform featuring a 5-layer caching architecture, LlamaIndex orchestration, and token economics monitoring.

    Python