Skip to content
View kbob3687-hub's full-sized avatar
๐ŸŽฏ
Focusing
๐ŸŽฏ
Focusing
3 followers · 2 following

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Sharkx2Achievement: YOLO

Block or report kbob3687-hub

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 donโ€™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 userโ€™s behavior. Learn more about reporting abuse.

Report abuse
kbob3687-hub/README.md

Hi, I'm kbob ๐Ÿ‘‹

Typing SVG

Build systems that survive the demo.

็›ฎๅ‰ไธป่ฆๅ…ณๆณจ AI Agentใ€้•ฟๆœŸ่ฎฐๅฟ†ใ€ๅคšๆ™บ่ƒฝไฝ“ๅไฝœไธŽๅŽ็ซฏๅฏ้ ๆ€งๅทฅ็จ‹ใ€‚

๐Ÿง  What I'm Building

Pi ร— TencentDB Agent Memory

A native Pi adapter for durable cross-session memory and reusable skill learning.

  • L0โ€“L3 bounded memory recall
  • Durable capture & offline recovery
  • Cross-process lease and retry
  • Skill learning โ†’ Pi native Skills
  • Branch isolation & fail-open design
  • Unit tests + real Pi / MemoryCore E2E verification

Open-source PR: TencentCloud/TencentDB-Agent-Memory#1070

๐Ÿค– AgentDrivenCompetBench

A multi-agent competitive intelligence system built around a real QA feedback loop instead of a linear Agent pipeline.

LangGraph ยท FastAPI ยท Vue 3 ยท Pydantic ยท SSE ยท Langfuse

Discovery โ†’ Collector โ†’ Analyst โ†’ Writer โ†’ QA
                                      โ†“
                          Pass / Revise / HITL

Focus:

  • Multi-Agent orchestration
  • QA-driven iterative revision
  • Evidence traceability
  • Human-in-the-loop
  • LLM observability

๐ŸŒŒ LuminaCampus-AI

An AI application exploring the combination of backend systems, Agent runtimes and knowledge retrieval.

Java ยท Spring Boot ยท Python ยท FastAPI ยท GraphRAG ยท Neo4j

๐Ÿ”ญ What I Care About

Agent Memory        โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ
Multi-Agent         โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘
Backend Engineering โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘
RAG / GraphRAG      โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘โ–‘โ–‘
Observability       โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘โ–‘โ–‘โ–‘
  • ๐Ÿง  Agent Memory & Context Engineering
  • ๐Ÿค– Multi-Agent Systems
  • โš™๏ธ Backend Reliability
  • ๐Ÿ”Ž RAG / GraphRAG
  • ๐Ÿ“Š LLM Observability
  • ๐Ÿ› ๏ธ Open Source Engineering

๐Ÿ›  Tech Stack

Backend

Java Spring Boot Python FastAPI MySQL PostgreSQL

AI / Agent

LangGraph GraphRAG Langfuse Pydantic

Engineering

TypeScript Git GitHub Actions SSE

โœ๏ธ Writing

ๅถๅฐ”่ฎฐๅฝ•็œŸๅฎžๅผ€ๅ‘่ฟ‡็จ‹ไธญ้‡ๅˆฐ็š„้—ฎ้ข˜๏ผŒ่€Œไธๅชๆ˜ฏๆ•ด็† API๏ผš

  • Agent Memory / Context Engineering
  • Multi-Agent ๆžถๆž„ไธŽๅฏ้ ๆ€ง
  • RAG / GraphRAG
  • ๅˆ†ๅธƒๅผ็ณป็ปŸ
  • ๅŽ็ซฏๅทฅ็จ‹ๅฎž่ทต

Keep building. Keep shipping.

Pinned Loading

  1. LuminaCampus-AI LuminaCampus-AI Public

    ๅŸบไบŽ Java DDD ไธŽ Python FastAPI ๅผ‚ๆž„ๆžถๆž„็š„ๆ กๅ›ญๅ…จๆ ˆ AI ๅŠฉๆ‰‹ใ€‚ๅˆฉ็”จ Neo4j + GraphRAG ๅฎž็Žฐๅญฆไธš่ทฏๅพ„ๆทฑๅบฆๆŽจ็†๏ผŒ้€š่ฟ‡ๅคšๆ™บ่ƒฝไฝ“๏ผˆMulti-Agent๏ผ‰ๅๅŒๆไพ› 1v1 ็ฒพๅ‡†ๅฏผๅญฆๆœๅŠกใ€‚

    Java

  2. AgentDrivenCompetBench AgentDrivenCompetBench Public

    ๅคšๆ™บ่ƒฝไฝ“้ฉฑๅŠจ็š„็ซžๅ“ๅˆ†ๆž็ณป็ปŸ๏ผŒLangGraph็ผ–ๆŽ’+QAๅ้ฆˆ้—ญ็Žฏ

    Python 5

  3. pi-agent-memory-adapter pi-agent-memory-adapter Public

    Unofficial Pi.dev adapter for TencentDB Agent Memory, adding durable cross-session memory, branch isolation, and learned skills to Pi.

    TypeScript 1