Skip to content
View lokesh75-kank's full-sized avatar
2 followers · 1 following

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLO

Block or report lokesh75-kank

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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
lokesh75-kank/README.md

🌱 Open-source contributions

  • OpenHands (83K★, open-source AI software engineer) — fixed automation cards silently dropping required integrations that can't be installed as MCP servers, with i18n and regression tests · Issue #16292 → PR #16324 (merged)
  • DeepEval (17K★, LLM evaluation framework) — found and fixed nonexistent Claude model IDs that made every default-configured Anthropic evaluation fail with a 404 · Issue #2993 → PR #2994 (in review)
  • DeepEval — found and fixed the judge's 1024-token output cap silently truncating responses on thinking-enabled Claude models, surfacing as cryptic invalid-JSON metric errors while thinking tokens were still billed · Issue #3042 → PR #3043 (in review)
  • LiteLLM (56K★, LLM gateway) — traced a user's /v1/v1/messages 404 to the one Anthropic passthrough config missing trailing-/v1 normalization, answered the report, and fixed it · Discussion #36651 → Issue #36956 → PR #36957 (in review)

Pinned Loading

  1. agenteval agenteval Public

    Reliability and audit-evidence testing for LLM agents - wrap any agent, assert behavior, measure determinism, check grounding, emit an audit-grade report.

    TypeScript

  2. deepeval deepeval Public

    Forked from confident-ai/deepeval

    The LLM Evaluation Framework

    Python

  3. litellm litellm Public

    Forked from BerriAI/litellm

    The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…

    Python

  4. OpenHands OpenHands Public

    Forked from OpenHands/OpenHands

    🙌 OpenHands: AI-Driven Development

    TypeScript

  5. langchain-ai/langchain langchain-ai/langchain Public

    The agent engineering platform.

    Python 144k 24k