Eyal Toledano

Sick of @cursor_ai rewriting good code or going in circles? Introducing Task Master ✨ A CLI that turns your PRD into a local task management system for Cursor Agent Graduate from building cute little apps to ambitious projects without overwhelming yourself or Cursor 👀👇

@breath_mirror @bstnxbt Is the output still coherent? I tried dflash with mlx and besides the benchmarks, the outputs became garbage. Even with the dlash drafters mlx lm has native drafting features, not as good as dflash but still a 25%-50% boost depending on the size + quantization of the drafter

left my pi-autoresearch all night long qwen3.6 went from ~80 tok/sec to ~180 tok/sec with @bstnxbt's dflash implementation as i'm running oMLX, had to port a bit as it wasn't working at the beginning

@nicoalbanese10 Congrats Nico, what an awesome relase Kudo upon kudos

3 months ago I started building a coding agent that runs in the cloud. It's since written every line of code I've shipped, including itself. Today, I'm open sourcing it. Introducing Open Agents.

The more enterprises I talk to about AI agent transformation, the more it’s clear that there is going to be a new type of role in most enterprises going forward. The job is to be the agent deployer and manager in teams. Here’s the rough JD: This person will need to figure out what are the highest leverage set of workflows on a team are (either existing or new ones) where agents can actually drive significantly more value for the team and company. In general, it’s going to be in areas where if you threw compute (in the form of agents) at a task you could either execute it 100X faster or do it 100X more times than before. Examples would be processing orders of magnitude more leads to hand them off to reps with extra customer signal, automating a contracting review and intake process, streamlining a client onboarding process to reduce as many straps as possible, setting up knowledge bases than the whole company taps into, and so on. This person’s job is to figure out what the future state workflow needs to look like to drive this new form of automation, and how to connect up the various existing or new systems in such a way that this can be fulfilled. The gnarly part of the work is mapping structured and unstructured data flows, figuring out the ideal workflow, getting the agent the context it needs to do the work properly, figuring out where the human interfaces with the agent and at what steps, manages evals and reviews after any major model or data change, and runs and manages the agents on an ongoing basis tracking KPIs, and so on. The person must be good at mapping the process and understanding where the value could be unlocked and be relatively technical, and has full autonomy to connect up business systems and drive automation. This means they’re comfortable with skills, MCP, CLIs, and so on, and the company believes it’s safe for them to do so. But also great operationally and at business. It may be an existing person repositioned, or a totally net new person in the company. There will likely need to be one or more of these people on every team, so it’s not a centralized role per se. It may rile up into IT or an AI team, or live in the function and just have checkpoints with a central function. This would also be a fantastic job for next gen hires who are leaning into AI, and are technical, to be able to go into. And for anyone concerned about engineers in the future, this will be an obvious area for these skills as well.

@Abdu_RRD @usehamster appreciate you!

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

@par4ma @usehamster 👀

@EyalToledano @usehamster need a post / breakdown of how, esp when knowledge is scattered across slack / notion etc

our context graph came to life today - full decision lineage - self-healing, self-updating team state - graph expanding as the team works - knows why we did what did when we did it AS WE DO IT, across the whole team everyone’s building infrastructure to read organizational knowledge. we’re building where it gets created. it’s what happens when alignment generates context as exhaust instead of losing it to slack threads holy shit we are never going back

kudos @harveyfullstack @maxtuzz shipping like demons

@maximumagi this is what the context graph is meant to power it’s not just for personal knowledgebases :)

cool stuff!

@aaronmakhoffman @usehamster yep! we finally have multiplayer claude code

@EyalToledano @usehamster Is this hamster?

@tonyennis @blakeandersonw @HilaShmuel @dotta Add tryhamster.com to the mix :)

Ai workspace tools I’m now tracking: - core.so by @blakeandersonw - runcabinet.com from @HilaShmuel - paperclip.ing from @dotta - getoperator.cc from yours truly

@bensig good shit ben

My friend Milla Jovovich and I spent months creating an AI memory system with Claude. It just posted a perfect score on the standard benchmark - beating every product in the space, free or paid. It's called MemPalace, and it works nothing like anything else out there. Instead of sending your data to a background agent in the cloud, it mines your conversations locally and organizes them into a palace - a structured architecture with wings, halls, and rooms that mirrors how human memory actually works. Here is what that gets you: → Your AI knows who you are before you type a single word - family, projects, preferences, loaded in ~120 tokens → Palace architecture organizes memories by domain and type - not a flat list of facts, a navigable structure → Semantic search across months of conversations finds the answer in position 1 or 2 → AAAK compression fits your entire life context into 120 tokens - 30x lossless compression any LLM reads natively → Contradiction detection catches wrong names, wrong pronouns, wrong ages before you ever see them The benchmarks: 100% recall on LongMemEval — first perfect score ever recorded. 500/500 questions. Every question type at 100%. 92.9% on ConvoMem — more than 2x Mem0's score. 100% on LoCoMo — every multi-hop reasoning category, including temporal inference which stumps most systems. No API key. No cloud. No subscription. One dependency. Runs on your machine. Your memories never leave. MIT License. 100% Open Source. github.com/milla-jovovich…

We’re doing it because we can build anything. So the search bar becomes where you make an initial statement of intent. A lot of initial exploration (putting your finger on the thing you want) is easier to get to with chat. You can state your intent and refine it. This is happening because intent sets the direction the LLM will take, which is why the chat input is the least worst starting point. UI assumes intent, chat lets you deeply explore it UI replacing chat is unlikely for deterministic flows though.

notice something? Linear, PostHog, Attio - all shipped the same thing in the last few weeks. Homepage is a chat bar - not a dashboard. This is the SaaS industry quietly admitting that traditional UI doesn't work anymore. Every user is different. One homepage can't serve them all. The playbook is shifting: → expose your core APIs → connect an agentic layer → let users use software the way they want SaaS became chat. Chat will become Generative UI - the agent won't just reply in text, it will compose the interface itself. We're closer than people think.

@MaxJunestrand @gustaf @WeAreLegora absolutely phenomenal

I want to take a moment to recognize a gravity-defying achievement by the entire @WeAreLegora team. We have grown from $1M to $100M in annual recurring revenue in just under 18 months. In this time, we've grown into a truly global company with over 400 colleagues - and built the platform where legal work happens. Powering more than 1,000 teams worldwide. It is all about the people, and I couldn’t be prouder of the Legora team and thankful to our customers and partners. This achievement is as much yours as it is ours.

@charlieholtz @conductor_build @ilyasu @nabeel @ycombinator major congrats friends

Big news for @conductor_build! We've raised a $22m Series A from Spark and Matrix. We raised this round from @ilyasu at Matrix, who also led our seed round and is joining our board, @nabeel at Spark, @ycombinator, and founders of Notion and Linear. We're grateful to be working with investors we trust and admire. Here’s how we got here and where we’re going:

@PaulJun_ Go paul!

I'm on the lookout for a builder, a T-shaped person who has deep mastery in brand design, building things (web and products), who has a learner's mindset and feels like their career is just beginning. Someone who is tired of the traditional brand design role in tech, who wants to work closely with various teams driving business outcomes, who wants to live on the frontier of AI. My team is working on things like the future of internal tooling, brand identity and systems, brand experiences (you get to work with my best bud @ItsJonHowell). We've already built multiple internal tools that can automate whitepapers, decks, and other assets. We're building things that don't exist yet. No official job description yet. Just looking to have conversations with people who wants to work with a team that's redefining the DNA and metabolism of a typical brand design team. Here's how I think how brand design is evolving: pauljun.substack.com/p/how-brand-de… Why I believe a point of view is more interesting than people who yap about taste: open.substack.com/pub/pauljun/p/… Why the future is about builders, small teams, that can own product develop, brand design, and the launch end to end: open.substack.com/pub/pauljun/p/…

@a_somervell @hshah18 @linear @karrisaarinen @usehamster

@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).

How soon till @linear launches a replacement for Notion? I want my knowledge base to be in the place where my work is happening. There I said it, @karrisaarinen.

@helloitsaustin @hnshah @AnthropicAI but austin they said ads were bad!

if you're a performance marketer, here's how I use a custom Claude Cowork plugin to manage Google Ads at @AnthropicAI. it connects to the Google Ads API via MCP, encodes my common paid search workflows into skills, and works on desktop and Dispatch.

@ryancarson @corazoncap @saramfoster @efosta @HamelHusain @shl The start of a great journey Best of luck Ryan!

Just closed our $2m seed round. We're building an agent for a very specific consumer pain point. Once we scale to more states, I'll share more. I'd like to thank our investors for putting their chips on us! Lead: @corazoncap Angels: @saramfoster @efosta @HamelHusain @shl @HenryLSchuck @thrashr888 @jheitzeb @SteveMorin @kkliman @i_am_brennan @zachtdavidson @LexSokolin @hillarycbush @usiegj00 @WindAddict Matthew Collins, Greg Smith and Jed Rhoads

@ryancarson it’s chef’s kiss, just like your setup

@EyalToledano lol love that gif

I haven't typed `npm run dev` on my local machine for three days now and it's absolute bliss. Having my agents 100% in the cloud is a massive unlock. (One of those agents is openclaw, which is technically on my mbp in my office, but the only way I interact with it is via email/slack so it “feels” cloud) I'm able to run all the engineering and marketing for my startup through Slack and Linear and because of this the work product that I'm shipping has increased dramatically. I know all of us devs love creating our own custom solutions to this stuff but the truth is that creating an agent orchestration layer for your company or startup is a full-time job. Our job as startup founders is to be growing the company, not to be building out an agent orchestration custom platform. I think if you have a larger engineering team like Ramp, then it does make sense to build an entire layer like Inspect agent. However, I would venture to say that I'm getting most of the value by simply paying for a pre-built, battle-hardened solution like Devin. Again to be clear I'm not being paid by Devin or anybody to say these things, just my real-world experience using this stuff.