AI / Agent application developer · Monash AI master's · Class of 2026
Huang Yihang
Turning LLMs into Agents that actually get things done.
From multi-agent cross-validation to desktop-grade autonomous execution — memory architecture, safety sandboxes, tool calls, all the way to production.
AI twin · tap to start chatting
The headlines first.
Swipe to browseFlagship open-source project · solo build · MIT, free and open
NoWorries NoWorries
Say it once. Leave the rest to it.
Electron + TypeScript + Python, built from scratch by one person.
One sentence — it plans, calls tools, and executes across multiple steps on its own.
Files never leave your machine. Every step can be rolled back.
Memory system
Three tiers of memory. It gets you, the more you use it.
Local SQLite · vector embeddings + semantic search · incremental summarization · emotional tagging
Worst case, you lose a couple of minutes.
Workspace isolation, automatic backups before any change, dangerous-command blocking, sensitive-path protection, a full operation log, and one-click undo. Deleted something? There's a backup. Changed the wrong thing? It was working on a copy. Even first-timers can hand it real work.
Learning a new skill is as easy as installing an app.
Skills are plug-and-play, community-shared, customizable to build, and versioned — from professional Excel / Word / PPT handling to automating internal company workflows, discovered and registered automatically at runtime.
Use your own key, no subscription fee — Zhipu GLM · Tongyi Qianwen · Doubao · Kimi · DeepSeek · Ollama (local, offline)
“The point of technology isn't to make people busier — it's to earn people the right to have no worries.”
Open-source contribution · OpenClaw
Understood OpenClaw's memory system, then rewrote the whole thing.
Upstream used single-layer vector retrieval — one embedding failure and it all collapses. I rebuilt it into three-tier cognitive memory + a four-tier fallback, so it can forget and always recover.
Degrade tier by tier — always an answer.
Three-tier cognitive memory
Rebuilt upstream's single-layer vector retrieval into three tiers — retrieval engine / cognitive memory / scheduling — so memory can forget and actively surface what matters.
Four-layer context management
Entry-point truncation, three-stage progressive trimming, persistent-session cleanup, plus a CJK-aware token budget — correcting roughly 40% token underestimation in Chinese-language cases.
Open framework · designed solo
Sprout — a task tree that grows itself.
Every Agent decides its own splits — a tree topology, unbounded depth, truly recursive.
Every Agent decides for itself whether to split.
Stuck? Detect it, cancel it, re-split.
Done nodes die, results bubble up.
Same task (write 4 independent Python modules), under a capped single-call budget: a single Agent scores just 25, while Sprout takes the full 100.
Scored automatically by a programmatic rubric, out of 100, reproducible. The single Agent runs out before finishing and gets truncated by token limits; after Sprout splits, each child node gets its own budget, and all 4 modules ship — the core value isn't parallel speedup, it's getting around the token / attention bottleneck of a single call.
Two-phase Worker
analyze() uses a lightweight call to first judge “should this split?”, then execute() does the real work. Separating analysis from execution makes the split decision sharper.
Approach injection
When a parent splits, it generates a methodology and focus for each subtask and injects them into the child Agent's system prompt — roles emerge from the task rather than being predefined.
Safety bounds
max_depth · max_children · max_total_nodes · max_total_tokens — four ceilings to keep the tree from exploding; 24 unit tests cover the core modules.
ContractLens · built with a practising lawyer
Read a 348-page contract down to one clear page.
AI review of Victorian (Australia) property contracts — a 10-stage pipeline, 7 AI analysts in parallel.
Upload the contract PDF; the rule engine splits it automatically.
7 AI analysts get to work in parallel.
A one-page report — every conclusion cited to the source.
Every conclusion holds up to scrutiny.
Mandatory source citations + rapidfuzz fuzzy-match verification + targeted retries only on failed citations; output then passes two compliance gates (regex + AI semantic review), ruling out “AI-lawyer” overreach.
Benchmarked against real lawyer reports.
4 real contracts (104–348 pages, including scanned OCR and a 5-address mixed-title case) ran end to end; compared line by line against a practising lawyer's review — about 30 findings matched the lawyer's report, plus 2 ACN discrepancies confirmed line by line with the lawyer that their report hadn't itemized.
Proven in production.
Two internships, putting Agents into real business.
Sugon · Agent Development Intern
2025.12 – 2026.02Agent application development — Built an intelligent HR Agent and enterprise RAG Q&A on Dify, with vector-store integration and chunking-strategy tuning, reaching 85%+ Q&A accuracy.
Multi-agent cross-validation — Three specialized review Agents independently assess SFT training items, with structured scoring + conflict arbitration for joint decisions — cutting manual review cost significantly.
SFT data engineering and QC — An automated QC workflow on Feishu validates 500+ items a day, cutting manual effort from 3 hours to 10 minutes; reviewed Tool Calling and CoT correctness line by line.
Fantuan · AI Product Intern
2024.11 – 2025.02Product iteration and validation — Drove 4 versions of the AceEssay AI-reduction tool, with a dual Turnitin / GPTZero evaluation framework, bringing the AI-detection rate from 100% down to 10–20%.
Content growth and SEO — 60+ pieces of content drove 75K site visits and grew followers from 0 to nearly 30K; core-keyword ranking went from 48 to 9, with organic traffic up roughly 3× month over month.
More work.
Chenxi Flowers inventory & sales system
An end-to-end operations system spanning stock in/out, ordering, pricing, and write-offs; zero-ops storage on Feishu Bitable, with on-site H5 mobile entry. Over ¥200K in cumulative sales.
Flask · Feishu OAuth · RailwayKaggle · Top 10%ViT image classification
Fine-tuned ViT / DeiT with layer-wise learning rates + Label Smoothing + RandAug / Mixup / CutMix, reaching ≈98% validation accuracy.
PyTorch · TransformersReinforcement learningDQN multi-agent transport
4 Agents on a shared-network DQN with a collision-avoidance priority scheme — 95% round-trip transport success, average steps down 20%.
DQN · Multi-AgentEaster egg · this very website
This keynote is itself an exhibit.
Read the full build log (in Chinese) ›Built with Claude Code, every step from one vague request to launch is on the record — the real prompts, the time each stage took, and every time the AI went off the rails and how I corrected it, all public in the build log (written in Chinese).
Tech specs.
One more thing.
This one is alive.
Every product demo above was an animation. This window is the real thing — my AI twin is live: it answers from a real résumé, and says so plainly when something's outside what it knows. How it works ›
Hi — I'm the AI twin of the person behind this site. I answer from their real résumé and project history, and I'll tell you straight when something isn't in my notes. Start with one of these:
Tell me about yourself
I'm Huang Yihang's AI twin. He's an AI master's student at Monash University (graduating July 2026), targeting LLM / Agent application development roles, based in Chengdu and open to remote. He did an Agent development internship at Sugon, independently built the open-source desktop AI assistant NoWorries, landed a merged PR on the open-source project OpenClaw, and wrote his own multi-agent framework, Sprout. Want the full picture? See the Projects and About pages.
When can you start?
He can start a remote internship right now; for full-time, he's available as soon as he finishes his master's in July 2026. He's based in Chengdu, comfortable working remotely, and the overseas degree certification doesn't slow down a remote start. In short: internship anytime, full-time the moment he graduates.
Are you open to remote work?
Yes—remote-friendly, and happy to come on-site or travel when it matters. He's based in Chengdu and open to both internship and full-time roles. The remote toolchain (Feishu, Git, async communication) is something he's actually run, both during his Sugon internship and while building this site collaboratively.
What sets you apart?
In one line: building from zero, reading and refactoring someone else's system, and shipping Agents into real enterprise workflows—he has verifiable work in all three. NoWorries is an open-source desktop Agent he built solo (three-tier memory + safety sandbox). OpenClaw was about understanding an active official project and refactoring its memory system, with the PR merged. At Sugon, he landed multi-agent cross-validation inside a real SFT quality-control pipeline. Most candidates can show one of the three. He has the real thing in all three.
Pick a project and tell me about a hard bug
Here's a real one: while refactoring OpenClaw, he found the official token estimate for Chinese (CJK) was off by roughly 40% on the low side—which threw off every upstream context-trimming strategy and blew the token budget constantly in Chinese scenarios. He added a CJK-aware token-budget correction layer to stabilize it. More wrong turns and corrections (including the ones the AI itself made) are all laid out in the build log—ask me about any detail and I'll take it down to the mechanism level.
How do I reach you?
Email: 1653120857@qq.com, GitHub: github.com/hlbbbbbbb. You'll also find every contact method on the About page, or you can download the résumé PDF / save the digital business card. And if you're a recruiter—he replies a lot faster than I do :)
AI-generated answers can be off — for anything that matters, go by the résumé and a conversation with me directly. Chats may be logged to improve the twin.
Fallback chain: real AI → FAQ demo → static page · fully readable with no JS
Let's build something that thinks.
Graduating with my master's in 2026.07, looking for a full-time LLM / Agent application development role (open to interning now). Send an email — I'll reply fast.
