Skip to content
View ktz03's full-sized avatar

Block or report ktz03

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
ktz03/README.md
Hi, I'm LI. AI Ecosystem Builder.

Core contributor to Microsoft Agent Framework, ByteDance’s OpenViking, and Tencent’s ncnn.
I build reliability into the systems that agents depend on, from workflow recovery and persistent memory to inference on edge devices.

My research focus is embodied AI and world models. How should an agent change its next move when the world differs from its prediction?

Shenzhen, China  ·  Website  ·  X

Three layers of AI infrastructure

Project and role What changed upstream
Microsoft Agent Framework · Core contributor Workflow recovery. I changed thread snapshots to retain a human reply so a workflow can resume with the answer already given. Contribution record · Historical PR #8273
ByteDance’s OpenViking · Core contributor Agent memory. I coauthored the LangChain fix that lets a restored conversation retain what was said, who said it, and which tools were called. PR #6275, opened by @ehz0ah · Coauthor credit
Tencent’s ncnn · Core contributor Inference reliability. I stabilized LogSumExp on CPU and Vulkan. Both backends now return a finite result for inputs like [1000, 1000]. PR #7055 · Numerical example

Of the 113 merged PRs across 35 upstream projects in my November 14, 2026 record, 72 are in the three projects above. I opened 99 of the 113 and am credited as a coauthor on the other 14.

Collaboration

View 14 coauthored PRs

Embodied AI and world models

A robot can finish a grasp motion while the object stays on the table. That gap is the problem I’m working on in embodied AI. A world model predicts what an action will change. The next observation gives the agent evidence to continue, retry, or choose a different action.

Agent developer tools I created

  • handoff-pack carries context between models or sessions. It prioritizes instructions, tool errors, and recent messages, then writes a compact Markdown or JSON handoff. Example conversation.
  • traj-wash prepares agent trajectories for evaluation and supervised fine-tuning. It keeps the first failed step as evidence and trims the retries that follow. In the seven-step example, four steps remain.
Full contribution record and more project cases

Browse publicly searchable authored PRs.

🤖 Microsoft Agent Framework · Agent workflows

Agent workflows · Recovery · Checkpoints

Agent orchestration, recoverable workflows and checkpoints. In the historical snapshot: 30 authored and 2 coauthored PRs.

The repository and historical PR links were unavailable when checked on November 18, 2026; the figures are from earlier verified records.

🧠 OpenViking · Agent memory

Agent memory · Context · Integrations

Memory, context and agent integrations. In the historical snapshot: 22 authored and 8 coauthored PRs.

⚙️ Tencent ncnn · Inference

Inference · Correctness · Portability

Inference correctness, portability and bindings. In the historical snapshot: 7 authored and 3 coauthored PRs.

More selected upstream work

Selected work: fixes that landed upstream

My contribution loop: reproduce the failure → preserve normal behavior → add a focused regression → close the review loop.

Further merged work includes TensorLy, PydanticAI, Qdrant Client, sklearn-onnx, RapidOCR, pyts, scikit-lego and Patsy.

Pinned Loading

  1. volcengine/OpenViking volcengine/OpenViking Public

    Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

    Python 42.5k 3.5k

  2. Tencent/ncnn Tencent/ncnn Public

    ncnn is a high-performance neural network inference framework optimized for the mobile platform

    C++ 24.1k 4.6k

  3. handoff-pack handoff-pack Public

    Multi-model Agent context handoff packet CLI — compress OpenAI-compatible messages into a paste-ready resume pack.

    JavaScript

  4. traj-wash traj-wash Public

    Agent trajectory diagnosis + rubric wash CLI — evaluate, locate failure onset, wash cascade failures, export clean segments.

    JavaScript