Skip to content
View Totoro-qaq's full-sized avatar
🎯
Focusing
🎯
Focusing
20 followers · 6 following

Achievements

Achievement: Pair Extraordinairex2Achievement: Starstruckx2Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex2Achievement: Starstruckx2Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Block or report Totoro-qaq

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. 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
Totoro-qaq/README.md

Hi, I'm Totoro.

AI Agent Harness Engineer & Full-Stack Engineer

I work on agent harness internals: runtime, state, memory, context and permissions.

Contributed to

Hermes Agent project website⁠Hermes Agent commits on main DeerFlow project website⁠DeerFlow merged PRs systemd project website⁠systemd merged PRs Apache Maka project website⁠Apache Maka merged PRs LobeHub project website⁠LobeHub merged PRs Cherry Studio project website⁠Cherry Studio merged PRs CopilotKit project website⁠CopilotKit merged PRs

Browse merged PRs →

Selected projects

  • dsh-plugin-bridge — Move sessions between DeepSeek Harness presets, with a preview before import.
  • Restork — A local-first desktop workspace for evidence-backed research, learning and work, with results kept as Markdown.
  • Cobsidian — A workflow for AI assistants to organize and maintain Obsidian vaults.

Tech stack

Languages & Frameworks

Python Rust C TypeScript Go

Infrastructure & Tools

Linux Docker Kubernetes AWS LangChain LangGraph Deep Agents Langfuse
OpenTelemetry Milvus PostgreSQL Celery

Models & Training

YOLO SFT LoRA / QLoRA DPO GRPO

Inference & Deployment

vLLM SGLang llama.cpp ONNX Runtime

Snake animation of Totoro's GitHub contribution graph

Icon credits

Pinned Loading

  1. dsh-plugin-bridge dsh-plugin-bridge Public

    DeepSeek Harness plugin for previewable cross-preset session migration. Fixed-schema handoffs preserve state, source-model intent, and unresolved images; the original session stays untouched.

    JavaScript 165 11

  2. Cobsidian Cobsidian Public

    Agent-agnostic workflow skill for maintaining Obsidian knowledge bases

    Python 14 3

  3. restork restork Public

    A desktop agent you can trust with files: preview every write, sandbox MCP tools, and keep Markdown local.

    Rust 4 1