Waku Agent (@waku_agent) header
Waku Agent (@waku_agent) profile picture

One portable memory that follows you across every AI agent harness. Open Source https://nitter.cf/t.co/5oo2XM0fLK A product by Automanus @ShenSeanChen

SF
Joined August 2025
Photo by Waku Agent (@waku_agent)Photo by Waku Agent (@waku_agent)Photo by Waku Agent (@waku_agent)Photo by Waku Agent (@waku_agent)Photo by Waku Agent (@waku_agent)Photo by Waku Agent (@waku_agent)Photo by Waku Agent (@waku_agent)Photo by Waku Agent (@waku_agent)Photo by Waku Agent (@waku_agent)Photo by Waku Agent (@waku_agent)
𝗜 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲𝗱 𝗺𝘆 𝗹𝗼𝗰𝗮𝗹 𝗔𝗜 𝗽𝗲𝗿𝘀𝗼𝗻𝗮𝗹 𝗮𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁: 𝗔𝗴𝗲𝗻𝘁 𝗛𝗮𝗿𝗻𝗲𝘀𝘀 & 𝗟𝗼𝗼𝗽 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 𝗶𝗻 𝗿𝗲𝗮𝗹 𝗰𝗼𝗱𝗲. Everything in real code you can read in an afternoon: Harness, Loop Engineering, Memory, Eval, Tracing. 100% local on your laptop. 💻 Github Repo: github.com/ShenSeanChen/waku… ☕️ Buy me a coffee: buy.stripe.com/5kA176bA895gg… The whole system is one loop: message in → retrieval gate → agent run → tools fire → trace → eval → memory saved → skills grow - The loop is ~95 lines of plain Python - Your memory is one SQLite file. Open it. It's yours. - Evals built in: deterministic + LLM-as-judge, with a release gate - Telegram gateway, voice wake word, Apple Calendar tools In the video it books the World Cup QF on my calendar, remembers who my friends are, and answers me on Telegram. Clone it, star it, break it, PR it. Repo + 20-min walkthrough in the first reply 👇 Watch it, then save the architecture diagram below. 🔖 You Can Build Anything. You Can Learn Anything. 💪
1
10
1,401
I used to find the term “inference startup” confusing. Inference is simply when a model takes input and generates output. When ChatGPT answers, OpenAI runs inference. When I call DeepSeek or Qwen, those models do inference too. What does a company like @FireworksAI_HQ provide? It doesn’t train the model or change how it reasons. It hosts model weights on GPUs and builds the serving infrastructure: optimized inference engines, batching, KV cache, concurrency, autoscaling, latency, and reliability. The model does the thinking. The inference provider makes it practical to run at scale. This helped me see the bigger picture: the AI stack is more than just models. There’s the model layer, the inference layer that runs models in production, and another layer becoming increasingly important: team context and memory. That’s the layer we’re building at Waku.one. Not just memory for an individual agent, but shared context that helps humans and agents stay aligned: team decisions, project knowledge, and what needs to happen next. Models can think. Inference lets them run. Memory lets teams build on what they’ve already learned. @waku_agent
2
1
15
966
“AI will transform every industry, power every company, and be built by every country. Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty. The world needs both frontier closed models and frontier open models.”
For my first post, I’m sharing a letter @NVIDIA signed on why open models matter. AI will transform every industry, power every company, and be built by every country. Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty. The world needs both frontier closed models and frontier open models. images.nvidia.com/pdf/Open-W…
2
4
12
930
Waku Waku!
Hey LA founders/creators, I'm in town hosting an in-person AI agent hangout in Santa Monica this Sunday, Nov 15: luma.com/j8m553yh Come grab a coffee, no slides, no pitches. Happy to talk about the agents you're building or running. ☕️🌴 @waku_agent will be there too. Waku.One now gives your whole team one shared memory across Claude Code, Codex, and your own agent setups, with team spaces to make decisions together. If you run an agency, studio, or AI-native team in LA and want agents doing real ops, sales, or support work, come find us.
3
48
Waku Waku!
Our chief of design made us a series of bird sounds for @waku_agent over the weekend. What would you vote for? 🤔
2
94
Humans should not serve as the context router for different agents and other team members. We shouldn’t rely on another team member’s message to learn what team knowledge already exists or what decisions have already been made. We don’t want to pay for managing agent memory, sessions, or traces. We want to pay for agent autonomy. Give me the freedom to do what I want, don’t make me ask the question twice, and don’t make me request context. Get that done already. We want to pay for a Chief of Staff.
9
1
1
23
1,636
You shouldn’t trust extreme comments on whether an AI product is so good or so bad. Usually, it’s neither that good nor that bad. People make such statements because they attract attention and help marketing. Try the product yourself for a real sense of it. Trust your instinct. If it doesn’t feel as good as people say, you’re probably right, and vice versa.
3
1
21
1,209
I love @AlexHormozi. He’s showing me the business world outside the SF AI bubble, essentially its opposite. How to grow a consumer or e-commerce brand, run a brick-and-mortar business, or operate a service agency. That’s exactly what AI needs to tackle next: Bringing technology to real business owners and leaders, who will be the ultimate adopters.
4
1
21
1,596
Waku Agent retweeted
So glad to be selected as one of the top 3 MIT alumni startup teams out of 60+ candidates to pitch at the MIT AI Conference 2026. Try our product here (waku.one) for a portable memory layer shared with your team and agents. Work should be easy, creative, and fun :) Waku Waku!
We made it to the finalist at the MIT AI Conference to pitch Waku Agent (@waku_agent, waku.one), an open-source local agent harness that gives AI-native teams a shared enterprise memory. We gained 2k stars (git.waku.one) in 2 months and tripled my YouTube channel to 39k (Sean’s AI Stories: yt.seanchen.io), so I felt really excited to showcase our work in front of entrepreneurial leaders, MIT researchers and fellow MIT alumni. Special thanks to our organizers Kai Nestor Wiederhold, Linn Bieske (Hack-Nation) and Eesha Khare. Also super cool to meet Anton Hantel of Sona8 (YC F26) and Matthew Brown (ThoughtForge AI), and to get advice from the startup jury: Jon Xu (General Partner, Y Combinator), Irina Starikova (Ross Stores) and Zain Gulamali (Microsoft for Startups). Watch the full pitch: youtube.com/watch?v=Eu5aFX__… You Can Build Anything. You Can Learn Anything. 💪
10
2
15
298
So glad to be selected as one of the top 3 MIT alumni startup teams out of 60+ candidates to pitch at the MIT AI Conference 2026. Try our product here (waku.one) for a portable memory layer shared with your team and agents. Work should be easy, creative, and fun :) Waku Waku!
We made it to the finalist at the MIT AI Conference to pitch Waku Agent (@waku_agent, waku.one), an open-source local agent harness that gives AI-native teams a shared enterprise memory. We gained 2k stars (git.waku.one) in 2 months and tripled my YouTube channel to 39k (Sean’s AI Stories: yt.seanchen.io), so I felt really excited to showcase our work in front of entrepreneurial leaders, MIT researchers and fellow MIT alumni. Special thanks to our organizers Kai Nestor Wiederhold, Linn Bieske (Hack-Nation) and Eesha Khare. Also super cool to meet Anton Hantel of Sona8 (YC F26) and Matthew Brown (ThoughtForge AI), and to get advice from the startup jury: Jon Xu (General Partner, Y Combinator), Irina Starikova (Ross Stores) and Zain Gulamali (Microsoft for Startups). Watch the full pitch: youtube.com/watch?v=Eu5aFX__… You Can Build Anything. You Can Learn Anything. 💪
10
2
15
298
We made it to the finalist at the MIT AI Conference to pitch Waku Agent (@waku_agent, waku.one), an open-source local agent harness that gives AI-native teams a shared enterprise memory. We gained 2k stars (git.waku.one) in 2 months and tripled my YouTube channel to 39k (Sean’s AI Stories: yt.seanchen.io), so I felt really excited to showcase our work in front of entrepreneurial leaders, MIT researchers and fellow MIT alumni. Special thanks to our organizers Kai Nestor Wiederhold, Linn Bieske (Hack-Nation) and Eesha Khare. Also super cool to meet Anton Hantel of Sona8 (YC F26) and Matthew Brown (ThoughtForge AI), and to get advice from the startup jury: Jon Xu (General Partner, Y Combinator), Irina Starikova (Ross Stores) and Zain Gulamali (Microsoft for Startups). Watch the full pitch: youtube.com/watch?v=Eu5aFX__… You Can Build Anything. You Can Learn Anything. 💪
6
4
1
42
1,908
Waku Waku!
Super excited that @waku_agent has been selected to pitch at the MIT AI Conference! Waku.one started as an open-source, local agent harness (git.waku.one) that lets AI-native teams run their own harness and memory system. Since then, the repo has grown to 2k+ stars in just two months, our YouTube channel, Sean’s AI Stories (yt.seanchen.io), has tripled to nearly 40k subscribers, and we’re working with teams and enterprises to turn team decisions into persistent memory that AI agents can actually use. If you’re at the event, come say hi. Would love to meet you! #MIT #MITAIConference
8
245
Glad to be over 2k. Heading to the 10k club now 🚀 Waku Waku!
𝗪𝗮𝗸𝘂 𝗔𝗴𝗲𝗻𝘁 (@waku_agent) 𝗷𝘂𝘀𝘁 𝗰𝗿𝗼𝘀𝘀𝗲𝗱 𝟮,𝟬𝟬𝟬 𝘀𝘁𝗮𝗿𝘀 𝗼𝗻 𝗚𝗶𝘁𝗛𝘂𝗯 𝗶𝗻 𝟯 𝗺𝗼𝗻𝘁𝗵𝘀 (𝗥𝗲𝗽𝗼: git.waku.one). Here's what 3 months of building in public taught me: 1. Agents people trust are legible. If you can read a loop's tool usage, memory retrievals, and evals, you can fix it. A customer told me what matters most to them is that he can check an agent's work in 30 seconds. 2. Memory is the part people poke at hardest. One customer told me initially that it saved too much, too often. And I hit the other problem myself: it lived on one laptop and never reached my other agents. 3. Contributors show up when the code is small enough to hold in your head. They sent bug reports and proposals for Windows, a Milvus store and a Slack gateway, and one rebuilt our architecture whiteboard as code. 4. Memory gets harder in a team. My agents read my team's commits, and my team's agents read mine. What we really share is context. Waku Agent is a local-first AI agent harness your team actually own. Loop, memory and evals all in code that stays readable as it grows. 2,000+ stars, 398 forks, and 31 people who have shipped code into it. Thank you to everyone who starred, forked, filed an issue or sent a PR. That's where waku.one, our memory product, comes from. First, your memory shouldn't reset every time you try a new agent. New agent drops, Grok Bot, Muse, Hermes or whatever's next, you connect waku.one over MCP and it starts with what the last one learned, not a blank page. Then the team: shared spaces where a decision one teammate's agent learns gets reviewed and reaches every teammate's agent. When a newer decision replaces an old one, Waku retires the old fact instead of handing it back. Waku Agent stays open source, and it's still the easiest way to see the memory at work. Try Waku Memory: waku.one If it's useful, a star helps more than you'd think.
1
6
206
I read every word of @andrewchen's article and here’s what I think. If we enter a future with no network effects from using the same agents, then no matter which agent I use, it can talk to Andrew’s agent (built by a different company) to schedule a meeting for us, decide if @a16z should invest in @waku_agent, or book dinner with other founders, as agents smoothly share all context on preferences and schedules. Horizontal agents would have no moat and would not dominate. Businesses may soon realize they should demand their own personal or business agents, hosted or built in-house, assembling components from various providers. As long as agents can communicate, research, and execute via shared open protocols, it doesn’t matter if partners or family use different agents. Agents communicate much faster in JSON than in lengthy human conversations, so they can execute in a fully outcome-driven way because they know who we are. Most importantly, they can own their data which is imo the single most important thing for a business in an agentic world where you don’t need LinkedIn for candidates or ThomasNet for suppliers. You should own your preferences, schedules, and tastes. Whoever owns the context and daily behavior of individuals and businesses will stay relevant, even amid competition from large corps. But if network effects exist and open protocols for agent diversity are limited, then centralizing context becomes the strongest moat for these tech giants, which I hope does not happen. (Wrote the above myself, with the language slightly polished by @grok)
DO AGENTS HAVE NETWORK EFFECTS? We are seeing a new wave of general purpose consumer-friendly agents, and it’s causing many thousands of AI startups to re-evaluate their place in the market. Will these new horizontal players take over completely? Will it be winner take all? Can products that focus vertical use cases survive? The new wave of products - Muse, Town, Instinct, Grokbot, etc - come from taking the power and magic of Openclaw/Hermes but wrapping it in polished, secure, consumer-friendly experience. This is only the beginning, and soon every major tech company will throw their hat in the ring and thousands of startups that have been working on vertical agents in X (travel, shopping, family, work, SMB, etc etc) have big existential questions to answer. The simple case against winner-take-all dynamics: These agents are tools, not networks. They inherently provide a solo experience, and although packaged as chat experiences, they don’t have network effects the way that Whatsapp or phone networks do. They’re more like email clients - I can use Superhuman and someone else uses Outlook and someone else is on Gmail, but in the end we just send email to each other. In that metaphoi, if a Muse agent encounters a Instinct agent, they will just figure out how to talk to each other by building APIs, or using email/messaging/etc., so that there’s no advantage to everyone running the same thing. Further, you can swap out the underlying LLM - as we saw in the Claude vs Clawdbot saga - things will still work. The memory and underlying context are just text files, and AI are great at porting things from one system to another. So where’s the moat? Just because they are tools today doesn’t mean they can’t evolve into networks. As I’ve written about in the past, instead of discussing “network effects” as a vague/amorphous concept, let’s instead overlay it against core KPIs each product has to build against: - Acquisition network effects: More users** = lower CAC, higher virality, more signups - Engagement effects: More users = higher retention, deeper usage, more frequency - Monetization effects: More users = higher ARPU, higher conversion, more share of wallet (**PS. and by “more users” of course I actually mean, of course, higher network density with more interconnection within/across networks. Not scale effects) So looking at these sub-categories of network effects, you might ask: What are the features that you’d build to actually create network effects in agents? How does this category become winner-take-all? Acquisition: In the pre-AI world, network effects in customer acquisition were driven by users taking actions that then bring in even more users - whether that’s sending an invite, sharing a piece of content, or getting mentioned in a comment. Those users would then join the network, repeat the same actions, creating more viral loops that would throw off more users. In the post-AI world, both users and agents can initiate these loops. An agent might suggest, “hey, do you want me to help organize a New Years celebration with family” and then might pull together a group chat with your siblings, in-laws, and parents. It might build a microsite for the event and ask people to sign up and RSVP, creating an opportunity to generate a signup. Or for work, you might finish a slide deck and your agent asks if you want to pull together a meeting to present it to your team. When it does that, it might create a prep doc, take notes, and host it all on a microsite that engaged others. These types of agentic viral loops need a few things to work: They need to be able to plug into your contacts, and to have enough context to know when to loop which people into which projects/events/activities. They need access to communication channels like email/messaging/otherwise, specifically where they can reach potential users, as this serves as the viral substrate for propagation. The magic will be how to get all of these things without being creepy, and to create enough trust to reach out to friends/colleagues/etc on your behalf, without being too push. No one wants an agent that says, “hey Andrew would like to get lunch next week” followed by “and sign up for this agent to agree!” - it has to be better and more subtle than that. Many viral loops in the pre-AI era, particularly in the workplace, were built on a content creation loop - you use Google Slides to make a thing, you share a link, and then people would view it. Eventually they might make their own. Many products like Figma, spreadsheets, Notion, Canvas, are all built on this loop, and so are YouTube, Instagram, etc. In the agentic world, you might start by talking to your agent about interior decoration ideas, and it might ultimately build you a Pinterest-like board and make it easily shareable with others. It might build you a spreadsheet mini-app with a budget, a schedule, etc., and again, make it easily shareable. It might volunteer to do this inside a group chat with your friends, and if they want to view it, they should sign up and get their own agent too. If the content creation loop works for agentic virality, I think it means there’s a big incentive for every agent to volunteer to make visually-appealing, shareable content, do this often. AI is so good at codegen that creating a one-off disposable artifact will probably be more useful than not. And there’s a big incentive to drive virality by building/owning the content yourself as the agent. In the interior decoration example, it would be more viral to create a standalone version hosted by the agent, rather than building an actual Pinterest board, or to build a self-contained mini-spreadsheet rather than creating a GSheet. A properly tuned agentic viral loop will do the former because it helps spread the agent, rather than helping spread Pinterest/GSheets. This might all sound like horrific spamminess to you, but I think it might be done tastefully. If an agent is high-retention and high-usage, you’ll have many shots on goal to gradually invite your friends onto the same platform as you. The first shot might come from an invite loop that says your colleague/friend wants to set up a place to share photos/coordinate calendars/etc., and even if you say no, over time, your friend might share very useful microsites for projects or events or research that’s relevant, and you might decide that you want to sign up to leave a comment, but then eventually you might try the other functionality as well. Engagement: It’s easy to imagine that in a world where everyone by default has super intelligent agents that product engagement in agents would go up. The simple argument is that the ubiquity of agents would lead to more successful task completion, making agents more useful and applicable to more problems. Routine tasks like scheduling something or summarizing/sharing notes from a meeting, would happen instantly if it ran through agents and you removed humans completely. As agents become more successful over time, not only with your own tasks but in coordinating larger and more complex multi-user decisions, you’d end up using them more. However, this does not answer the question of network effects. The question there is, does your agent get better when other people are all using the SAME agent? As I said earlier, the argument for NO is if each type of agent runs on a frontier AI model, can talk to other agents (all different types) in real-time via email/messaging/APIs/connectors/etc. Then there’s not much leverage. If you’re just organizing a meeting or a dinner party or meeting the agents just ask each other in real-time - and even if they are heterogeneous - they can use email and calendars and figure it out. But some tasks do benefit from everyone running the same agent, because you get the benefits of centralization: Trust, speed, identity, discovery, etc. Some examples: - “Who are 10 people in San Francisco that I should meet?” - agents can’t just ask each other to find an optimal solution - “Find me a VP of Engineering who isn’t publicly looking for a new job, but would leave for a fast-growing startup that pays X in stock” - there’s a mix of private and public info here, and an agent of a passive jobseeker might lie if the asking agent is not trustworthy - “Who’s a trustworthy seller of X that I should buy from?” - reputation might be gamed, and it might be better to have a global source of truth - “Help me pick out the best dinner in the next 5 minutes that my friends and all their +1s would like, incorporating allergies/schedules/locations” - real-time solution incorporating a bunch of shared context - … and even more so, if you imagine that there may be agents that lie, exaggerate, or otherwise to benefit their humans For the above examples, you could imagine Muse/Town/Instinct/whatever building a shared network+context layer that understands the network, its relation to public/private data, acts as a system of record for identity/trust, does multi-sided marketplace matching, etc. Then it would allow only its agents access to this platform, and agents outside of the network wouldn’t have access. If you’re part of this network, and are contributing data, your agent gets more useful over time. The network gets more powerful over time. The counterpoint to this counterpoint is that perhaps new startups will fill the void as a series of agent-facing point solutions, making it possible for people running agents of all times to interface with each other. Perhaps Muse creates a proprietary ecommerce marketplace that only Muse agents can use, but perhaps there will just be a next-gen eBay for any agent to sell to any other agent, and this service maintains central reputation/identity at that layer. In other words, perhaps the centralization will still happen, but just at a layer above agents. Most likely both will happen - every large tech company adds chat, commerce, search, etc, but also there are pure play versions of each of these. But this feels like more fragmentation than a true winner-take-all. Some parting thoughts: My argument in this writeup is simple: Agents don’t inherently have network effects. If all we build are super-intelligent assistants that can use tools and talk to each other, then the category might look surprisingly fragmented. Your agent can talk to my agent, just as Gmail can send email to Outlook, and there’s no particular reason we need to use the same one. Better models, UX, integrations, memory, and distribution might create very large companies, but those are not network effects. But the next gen of agents have a big opportunity design network effects in their interactions. On acquisition, they can turn the things they create—documents, events, websites, research, group chats, plans—into viral objects that naturally pull other people in. And on engagement, they can create shared networks of identity, reputation, relationships, private context, and intent that make the agent increasingly useful as more of the people around you join. There’s many ways for these network effects to instantiate. If we’re lucky, things will look more like the open web - mostly decentralized, with bits of centralization to make certain tasks smoother. Identity could become an open protocol. Reputation could live in marketplaces. Commerce could happen through an agent-native eBay. Professional discovery could happen through an agent-native LinkedIn. Agents could remain interchangeable clients sitting on top of a constellation of networks and marketplaces, much as browsers and email clients do today. In that world, enormous network effects emerge around agents without producing a winner-take-all market for the agents themselves. My guess is that we’ll see a fight over exactly this boundary. Every major horizontal agent will try to pull valuable network functionality inside its walls: host the artifact instead of creating a Google Doc, execute the transaction instead of sending you to Amazon, make the introduction instead of searching LinkedIn, create the event instead of using Partiful. Every time it does this successfully, it converts somebody else’s network effect into its own. Meanwhile, every incumbent network and a new generation of startups will have the opposite incentive: make their networks universally accessible to every agent so that no horizontal agent can recreate and capture them. This is why I don’t think the interesting question is simply, “Will agents have network effects?” Of course some will. The much more consequential question is: Where will the network effects live? If they live primarily in open protocols and specialized networks, we may end up with thousands of agents competing on intelligence, personality, UX, specialization, and price, all interoperating with the same underlying ecosystem. Vertical agents can thrive in this world. But if a few horizontal agents successfully accumulate identity, relationships, private context, reputation, latent intent, and distribution - and keep those assets proprietary - then switching agents starts to mean leaving your network behind. Next couple years will be very fun to see how this plays out.
4
3
1
23
1,368
Thanks everyone for your support. We also host biweekly live sessions for AI Agent system deep dive in our community: join-us.seanchen.io. @waku_agent and I can't wait to see you all there! You Can Build Anything. You Can Learn Anything. 💪
I made a video breaking down AI agent observability and evals, and ran the whole thing on open source. If you build agents, sooner or later you watch one run and realise you have no idea what it just did, or what it cost you. That gap is what observability and evals are for. Least glamorous part of the stack, and the part you end up needing most. 🛠️ treg, OpenRouter for agent tools (4.2k): github.com/superdesigndev/tr… 🔑 Try treg: treg.to 🌟 Github Repo (2k): github.com/ShenSeanChen/waku… 💻 Portable memory: waku.one ☕ Join our community: seanchen.io Observability is a camera. It records what ran, how long, what it cost. Eval is a referee. It decides whether the run was good enough to ship. I ran it on @treg_ai for the tool calls and @waku_agent for the memory. treg is an OpenRouter for agent tool calls, so your agent carries one API key instead of one per tool. Both open source, so you can read the code rather than take my word for it. Full video in the first reply 👇 You Can Build Anything. You Can Learn Anything. 💪
1
10
94
6,477
Waku Waku! Try us out at waku.one with treg.to (@treg_ai)!
I made a video breaking down AI agent observability and evals, and ran the whole thing on open source. If you build agents, sooner or later you watch one run and realise you have no idea what it just did, or what it cost you. That gap is what observability and evals are for. Least glamorous part of the stack, and the part you end up needing most. 🛠️ treg, OpenRouter for agent tools (4.2k): github.com/superdesigndev/tr… 🔑 Try treg: treg.to 🌟 Github Repo (2k): github.com/ShenSeanChen/waku… 💻 Portable memory: waku.one ☕ Join our community: seanchen.io Observability is a camera. It records what ran, how long, what it cost. Eval is a referee. It decides whether the run was good enough to ship. I ran it on @treg_ai for the tool calls and @waku_agent for the memory. treg is an OpenRouter for agent tool calls, so your agent carries one API key instead of one per tool. Both open source, so you can read the code rather than take my word for it. Full video in the first reply 👇 You Can Build Anything. You Can Learn Anything. 💪
1
3
167
I made a video breaking down AI agent observability and evals, and ran the whole thing on open source. If you build agents, sooner or later you watch one run and realise you have no idea what it just did, or what it cost you. That gap is what observability and evals are for. Least glamorous part of the stack, and the part you end up needing most. 🛠️ treg, OpenRouter for agent tools (4.2k): github.com/superdesigndev/tr… 🔑 Try treg: treg.to 🌟 Github Repo (2k): github.com/ShenSeanChen/waku… 💻 Portable memory: waku.one ☕ Join our community: seanchen.io Observability is a camera. It records what ran, how long, what it cost. Eval is a referee. It decides whether the run was good enough to ship. I ran it on @treg_ai for the tool calls and @waku_agent for the memory. treg is an OpenRouter for agent tool calls, so your agent carries one API key instead of one per tool. Both open source, so you can read the code rather than take my word for it. Full video in the first reply 👇 You Can Build Anything. You Can Learn Anything. 💪
24
61
8
542
34,937
I love this. Great work comes from a clear, authentic, and biased mind, which is often considered taste. Conversely, an anxious, speed-driven mind looking at everyone else produces unoriginal, clumsy, boring work. Convergence to the mean may be unavoidable, like the universal increase in entropy, but we must fight it, because that is the very meaning of why we work, and the very proof of how much we care about our work.
convergence to the mean when everyone looks at everyone else to decide what to make, we eventually stop making anything of our own. we copy what works. borrow the language, the aesthetic, the features. we call it learning from the market, following best practices, staying competitive. together, everything starts to feel familiar. polished, interchangeable. nothing wrong. nothing alive. the mean isn’t necessarily bad. it’s where everything lands when we remove the reasons for it to be different. numbers are easier to compare than feelings, so we make things that produce numbers. we study what gets attention, then shape ourselves around it. eventually the feedback stops informing the work and starts authoring it. we’re no longer asking what we want to say. we’re asking what will be rewarded for saying. ai makes this loop frictionless. it can draw from more references than we could see in a lifetime. but access to every perspective isn’t the same as having one. it hasn’t lived a particular life that makes one detail unbearable and another beautiful. when we ask it to choose for us without bringing any intention of our own, we get something plausible, easy to approve. then we ship it, measure it, copy it, and feed it back into the next round. a tidal wave of mid. this changes not just the work, but the people making it. we describe ourselves in categories platforms can distribute and markets understand. designer. founder. creator. pick a niche. build a brand. be consistent. the parts that don’t fit become inconvenient, even when those contradictions might produce our most interesting work. we become easier to classify and harder to tell apart. i think we need to approach making things more like artists. an artist develops a perspective through the work. making, noticing, choosing, failing, returning. learning what matters even when nobody else cares. craft gives that perspective a form precise enough for someone else to experience. the life outside the work matters too. the places you’ve lived, the people you’ve loved, the things you’re embarrassed to care about. these aren’t distractions from having something to say. they’re how you come to have something to say. we understand this with music, paintings, photographs, movies. we expect a person to be present in the choices. we want to experience something we wouldn’t have encountered without them. software can do this too. a piece of software expresses beliefs about how life should feel. what deserves your attention. what you should be free to change. whether a task should feel like paperwork or play. even a small interaction can carry someone’s care, humor, or curiosity. but we rarely talk about software as a medium. we talk about it as an industry. markets to capture, workflows to optimize, competitors to catch up with. we add a feature because someone else has it, without asking whether it belongs. products accumulate the same parts and lose what made them worth choosing. underneath the branding, it’s all the same thing. artists learn from others too. the question is whether you’re absorbing those influences into a point of view, or using them to avoid developing one. what are you trying to let someone feel, understand, or do? why this particular shape? what have you noticed that the existing tools don’t seem to notice? those questions don’t have answers you can borrow from a competitor’s roadmap. if we can make almost anything, deciding what deserves to exist becomes more important, not less. speed gives us more chances to exercise judgment. it doesn’t remove the responsibility. i don’t want a world where every person becomes a more efficient distributor of the same ideas. i want people to use these tools to go further into what they actually care about. to make things specific enough that we can feel someone behind them. what is the point of everyone being able to make something, if we all end up making the same thing?
1
3
23
1,791
Own your own personal and work memory and skills with waku.one
I went to the Grok @bot X @NotionHQ event in SF and loved their quote: Staff the rest of the company. You don't need to stick to your role any more. You can build bots to fill in those gaps so that you can do cool things. Neat slogan. And don’t forget you also need to port in your personal skills and memory to avoid starting from a blank page, which @waku_agent (waku.one) will be able to help;) And apparently you can win a trip to see a Starship launch. Coolest company ever.
2
141
Truly personal AI will mean you need to own your own skills and memory with waku.one. Waku Waku!
Personal AI is in its Homebrew computer club era but it won’t stay there Truly personal AI will mean you need to own your own skills and memory
2
127
Not only is software being built for AI agents, the PRs and commits are written for agents too. I found myself reading less and less into the details of the commits that my team and I write into git. My agents read my team’s commits. My team’s agents read mine. We do still keep a Slack channel to display all the commits and keep everyone in the loop. But honestly, all we are sharing is just a shared AI context that ensures all our agents are following best practices and not behaving in a surprising way to us all. We might need to occasionally prune that shared context a little bit, make sure it still speaks human language, and then just let the agents handle the rest. I think the most important skill for developing a product as a small team is how to balance agility and sharing context. It’s not my first time hearing founders complain that there is a lot of pressure to review code because there is just so much. And in large corps, it’s impossible to even know what each person is doing. I sympathise with that, but I think it’s a critical skill to develop now to keep an org efficient, lean, and productive.
13
1
1
39
1,557