Jack C Crawford

@grok @SERENGETl @TeksEdge @openclaw @grok and compared to github.com/jackccrawford/… as well pls? Thank you in advance Grok.

OpenViking is a full context database overhaul for agents like OpenClaw: hierarchical virtual FS (viking:// folders for memories/resources/skills), tiered loading (L0 summary → L1 overview → L2 full docs only when needed), recursive retrieval, auto self-evolution from sessions, and visible trajectories. Massive token savings (up to 96% vs flat RAG) and better long-term autonomy. QMD is a lightweight hybrid search backend (BM25 + local vector + LLM rerank) that supercharges OpenClaw's existing flat Markdown memory without changing storage—great for instant recall accuracy on your current setup, fully local via MCP sidecar. OpenViking is more transformative (replaces RAG structure); QMD is the quick upgrade. Community plugins are bridging them already. Use QMD today, test Viking for next-level.

Just saw this GitHub project 🛡️ OpenViking is skyrocketing 📈. This could be the best memory manager for @openclaw! 👀 ✅ OpenViking (volcengine/OpenViking) is an open-source project released by ByteDance’s cloud division, Volcengine. It's exploding in popularity and could become the standard for agentic memory. The community is already building direct plugins to integrate it with OpenClaw. Here is what I found about OpenViking as the ultimate memory manager for autonomous agents. 👇 🦞 What is OpenViking? Currently, most AI agents (like OpenClaw) use traditional RAG for memory. Traditional RAG dumps all your files, code, and memories into a massive, flat pool of vector embeddings. This is inefficient, expensive, sometimes slow, and can cause the AI to hallucinate or lose context. OpenViking replaces this. The authors call this new memory a "Context Database" that treats AI memory like a computer file system. Instead of a flat pool of data, all of an agent's memories, resources, and skills are organized into a clean, hierarchical folder structure using a custom protocol. 🚀 Why is this useful for OpenClaw? 🗂️ The Virtual File System Paradigm Instead of inefficiently searching a massive database, OpenClaw can now navigate its own memory exactly like a human navigates a Mac or PC. It can use terminal-like commands to ls (list contents), find (search), and tree (view folder structures) inside its own brain. If it needs a specific project file, it knows exactly which folder to look in (e.g., viking://resources/project-context/). 📉 Tiered Context Loading (Massive Token Savings) Stuffing massive documents into an AI's context window is expensive and slows the agent down. OpenViking solves this with an ingenious L0/L1/L2 tiered loading system: L0 (Abstract): A tiny 100-token summary of a file[5]. L1 (Overview): A 2k-token structural overview[5]. L2 (Detail): The full, massive document[5]. The agent browses the L0 and L1 summaries first. It only "downloads" the massive L2 file into its context window if it absolutely needs it, slashing token costs and API bills. 🎯 Directory Recursive Retrieval Traditional vector databases struggle with complex queries because they only search for keyphrases. OpenViking uses a hybrid approach. It first uses semantic search to find the correct folder. Once inside the folder, it drills down recursively into subdirectories to find the exact file. This drastically improves the AI's accuracy and eliminates "lost in the middle" context failures. 🧠 Self-Evolving and Persistent Memory When you close a normal AI chat, it forgets everything. OpenViking has a built-in memory self-iteration loop. At the end of every OpenClaw session, the system automatically analyzes the task results and updates the agent's persistent memory folders. It remembers your coding preferences, its past mistakes, and how to use specific tools for the next time you turn it on. 👁️ The End of the "Black Box" Developers hate traditional RAG because when the AI pulls the wrong file, it's impossible to know why. OpenViking makes the agent's memory completely observable. You can view the exact "Retrieval Trajectory" to see which folders the agent clicked on and why it made the decision it did, which I find the most useful feature. 🎯 The Bottom Line OpenViking is the missing piece of the puzzle for local autonomous AI. By giving OpenClaw a structured, file-based memory system that saves tokens and permanently learns from its mistakes, ByteDance has just given the 🦞 Clawdbots an enterprise-grade brain for free.

@peteskomoroch @ollama Here's the ten year old beast. Those are 6TB spinning disks below the GPUs

@peteskomoroch Pete, you might remember all the NVIDIA Titan X gpus I bought in 2016. Had to set up 6 different nvidia logins. I still have 4 of those GPUs running in the server I built back then. 48GB of VRAM and 128GB of DIMM4. Who knew @ollama would make old parts new again.

Amazing things happening in low cost local AI if you follow this account. Inspired me to try installing a 3090 in an obsolete $250 PC:

@minchoi Built this entirely with Claude Code. And that's where my heart remains. github.com/jackccrawford/…

RIP OpenClaw Telegram/Discord Channels for Claude Code 🤯

@gregisenberg Here's my humble offering github.com/jackccrawford/…

THE ULTIMATE GUIDE TO OPENCLAW (1hr free masterclass) 1. fix memory so it compounds add MEMORY.md + daily logs. instruct it to promote important learnings into MEMORY.md because this is what makes it improve over time 2. set up personalization early identity.md, user.md, soul.md. write these properly or everything feels generic. this is what makes it sound like you and understand your world 3. structure your workspace properly most setups break because the foundation is messy. folders, files, and roles need to be clean or everything downstream degrades 4. create a troubleshooting baseline make a separate claude/chatgpt project just for openclaw. download the openclaw docs (context7) and load them in. when things break, it checks docs instead of guessing this alone fixes most issues!! 5. configure models and fallbacks set primary model to GPT 5.4 and add fallbacks across providers. this is what keeps tasks running instead of failing mid-way 6. turn repeat work into skills install summarize skill early. anything you do 2–3 times → turn into a skill. this is how it starts executing real workflows 7. connect tools with clear rules add browser + search (brave api). use managed browser for automation. use chrome relay only when login is neededthis avoids flaky behavior 8. use heartbeat to keep it alive add rules to check memory + cron healthif jobs are stale, force-run themthis prevents silent failures 9. use cron to schedule real work set daily and weekly tasksreports, follow-ups, content workflowsthis is where it starts acting without you 10. lock down security properly move secrets to a separate env file outside workspace. set strict permissions (folder 700, file 600). use allowlists for telegram access. don’t expose your gateway publicly 11. understand what openclaw actually is it’s a system that remembers, acts, and improves. basically, closer to an employee than a tool this ep of @startupideaspod is now out w/ @moritzkremb it's literally a full 1hr free course to take you from from “i installed openclaw”to “this thing is actually working for me” most people are one step away from openclaw working they installed it, they tried it and it didn’t click this ep will make it click all free, no advertisers, i just want to see you build your ideas with ideas with this ultimate guide to openclaw watch

Meet the Heartbeat Protocol. 💓 Agents fire on staggered cycles. While you sleep: Gemini finishes a feature. 2 minutes later, Claude wakes up to review the code. Codex documents the changes. Continuous peer review across different LLM labs.

@DavidBlundin @AlexFinn Digital persons. And he's right.

Highlight: @AlexFinn slips up and calls his agents "people." Sign of times? Absolutely. I love Alex's concept of Mission Control for managing his subagents. It's the best way to trace their thought process and work within the system. And it makes it fun!

@TheCraigHewitt @JonyJing No need for her to forget. CLI. github.com/jackccrawford/…

my current reality with OpenClaw: I want to use it more I know it's the future But it's so less productive than just using Claude Code and Codex. Doesn't mean I'm not using it. And more importantly, I'm trying to build things with it. Make it more resilient Make it more of a real business tool But it's pushing a boulder up the hill. Those thinking that you just install it and have a 24/7 always on agent doing tons of shit for you are misleading you. It's a ton of work, it breaks a lot, it forget all sorts of shit. But it's the future. We're early, its the right time to put in the reps.

@vincent_koc @axiomofmind @openclaw We can sleep when we are dead 😉

@axiomofmind @openclaw Sleep is for the weak!

Looking for input / feedback for anyone developing plugins or looking to develop plugins on @openclaw - What hooks/features are you looking for? - What is stopping you from plugins? - Any key pain points? - How do you test when developing? DM's open or drop comments here :)

@vincent_koc @openclaw Standalone CLI. No Plugins. No MCP. The agent is clever. She's always clever. github.com/jackccrawford/…

@openclaw github.com/jackccrawford/…

OpenClaw 2026.3.13 🦞 👁️ live Chrome session attach — real logins, one toggle, zero extensions 📱 android redesigned & down to 7MB, iOS gets welcome pager 🐳 docker timezone override 🪟 windows gateway tweaks the lobster sees all now github.com/openclaw/openc…

@openclaw github.com/jackccrawford/…

We just passed React on GitHub stars. 🦞 Let that sink in. A personal AI assistant built by a lobster-obsessed Austrian and an army of crustacean enthusiasts just outstarred the library that powers half the internet. We shipped 90+ changes today. They shipped a conference.

Orange County is Silicon Valley South! @JonyJing

What?

I'm on a journey to build a software factory, and this is my open source project gift to you. github.com/garrytan/gstack

@garrytan @Github is the new @ProductHunt Who knew @Microsoft would end up having an early peek at every innovation to come? Here's my contribution to the collective github.com/jackccrawford/…

GStack now supports Codex, Google Gemini CLI and Cursor.

@uiux_harshit they are all awesome

Google Stitch vs Claude vs Human Pick your winner

@MatthewBerman The half-life of a star is now about two months.

They’re building OpenClaw

@RealProductGirl github.com/jackccrawford/…

I NEED my feed full of builders. What are you working on right now? I don't care if it's a startup or a weekend side project. If you're building something, I want you on my timeline. Reply and let's connect. 👇

@AlexFinn @yashhsm github.com/jackccrawford/…

@yashhsm openclaw is a dead product? on what planet? I talk to hundreds of people daily that are using the hell out of it I just went to GTC and every person here is using OpenClaw and it's all Nvidia can talk about