Max Tuzzolino

We're shipping

Not relying on mcp tools to collect context or keep it in sync is a wonderful feeling

@hshah18 @linear @karrisaarinen You're describing @usehamster, the AI-native workspace for product teams, where context compounds, and your whole team refines and aligns. The age of the product wiki that nobody keeps up to date has passed. And Hamster two-way syncs with Linear (who we love).

stability enables speed more than novelty ever will.

@michaelfreedman Supabase + RLS compatible?

Introducing TigerFS - a filesystem backed by PostgreSQL, and a filesystem interface to PostgreSQL. Idea is simple: Agents don't need fancy APIs or SDKs, they love the file system. ls, cat, find, grep. Pipelined UNIX tools. So let’s make files transactional and concurrent by backing them with a real database. There are two ways to use it: File-first: Write markdown, organize into directories. Writes are atomic, everything is auto-versioned. Any tool that works with files -- Claude Code, Cursor, grep, emacs -- just works. Multi-agent task coordination is just mv'ing files between todo/doing/done directories. Data-first: Mount any Postgres database and explore it with Unix tools. For large databases, chain filters into paths that push down to SQL: .by/customer_id/123/.order/created_at/.last/10/.export/json. Bulk import/export, no SQL needed, and ships with Claude Code skills. Every file is a real PostgreSQL row. Multiple agents and humans read and write concurrently with full ACID guarantees. The filesystem /is/ the API. Mounts via FUSE on Linux and NFS on macOS, no extra dependencies. Point it at an existing Postgres database, or spin up a free one on Tiger Cloud or Ghost. I built this mostly for agent workflows, but curious what else people would use it for. It's early but the core is solid. Feedback welcome. tigerfs.io

every time you start a new claude code session you spend the first 10 minutes re-explaining your project "here's the stack. here's what we're building. here's what was decided last week. here's the file structure. DON'T TOUCH THIS PART WE JUST REBUILT IT" but it's not just your own context. your teammates shipped 3 new things since yesterday, two architectural decisions changed and a dependency got swapped out. you need to capture all of that too, or claude is building from a stale snapshot you won't remember everything. so claude compiles context from scratch, misses things, and pulls in a direction that might completely miss the point. now multiply that by every dev on your team, every session, all day literal coordinated drift what we do instead: the .hamster folder syncs decisions, plans, and context to the filesystem automatically. claude reads it and just knows. no re-explaining. no stale snapshots. everyone's always got a fresh .hamster folder which updates in real-time as the rest of the team (or you) ship decisions, tasks, briefs, methods, skills, etc try it. you'll love it → @usehamster

everyone on your team maintaining their own CLAUDE.md is a symptom, not a solution. the root cause is that shared context has nowhere to live and evolve as your team makes decisions. you can't fix it with naming conventions or a better folder structure. decisions need a home. not a static file someone remembers to update. a workspace that accumulates as the team works. when a decision changes, it changes once, and every agent on the team pulls from that. there's no need to keep the markdown files up to date or copy-paste anything anywhere. claude just knows. your PRDs, your tasks, your skill files, your CLAUDE.md are all projections of the same underlying decisions. if the decisions live somewhere real, everything else stays aligned. if they stay up to date automatically, the rate of progress can explode because the synchronization overhead disappears. that's what we've been building into hamster. decisions get a home. blueprint holds your product's current state. methods encode how agents should work. the projections stay aligned because the source of truth is real. dm if you want to try it GA reeealllly soon!

@BoizHiver91548 @tom_doerr AI can USE something like this to get what it needs and what is relevant. It provides a traversable interface for LLMs to discover context. For those of us working heavily in the native AI applications + orchestration space these kinds of techniques are killer

@tom_doerr It's wrong! The main purpose of building knowledge graph is to move knowledge through your brain, structuring by yourself, to invoke memorizing. The notes system is secondary product, useful for quick recall. Otherwise, why is this needed if ai do all for u?

Extracts triplets from text into interactive graphs github.com/robert-mcdermo…

@MoonDevOnYT Cursor is still killing it. CC is great, but the Cursor DX is supreme.

Do people still use cursor? Or have we all moved on the claude code terminal mode only?

@g_korland @benln Context in Hamster studio lives as a node. There are close relations, and relations that are further away. Where you are and what you're doing within Hamster helps delegate what's relevant to you at that time. Chat grows like a tree, and it's aware of its branches.

@maxtuzz @benln Sounds interesting, what are you using Knowledge Graph?

What are you building this weekend? Share links, curious to see.

we've shipped huge features in taskmaster v0.37 🚀 → real-time PRDs, team plans, synced tasks 🐹 → GPT-5, @lmstudio, @Zai_org GLM → @claudeai plugin + @aisdk v5 → smaller MCP tool footprint → redesigned init ux → enterprise proxy + more follow + retweet + bookmark 👀👇

This almost felt like a product singularity moment for me building this. There was a point during development where I had run my n’th iterative tweak on this. I was planning a new feature for Hamster using Hamster and I realized how people build product is going to change

@danielrakh multiplayer chat is the next great collaborative ui we use it for teaming up to draft and refine PRDs and briefs that then get executed by background agents

@lgrammel Makes sense! Less options for achieving the same outcome is a good thing. Especially if it aligns with everything else you're building going forward.

Considering deprecating generateObject (and streamObject) in AI SDK 6. generateText with output would replace it. Benefits: reduced API surface (less to learn), structured output that works with tools, aligned with the agent abstraction Automatic migration should be possible.

@RalphEcom Same

Ai nerding all weekend. How about you guys ?

know incredible devs? paying $5K for successful referrals looking for: - senior TS engineers to own core pkgs for @usehamster - lead integration specialist to help me build context graph from tools we use daily - lead ML specialist w/ exp in custom model dev dms are open! 🐹

@usehamster's goal isn't merely @taskmasterai 2.0 We'll introduce a next-gen PM approach, Taskmaster-style, for the AI age We're ditching roadmaps, status updates, sprint planning etc In exchange for MAX velocity With AI connecting dots to ship fast The Hamster Way 🐹