alive ๐Ÿฟ๏ธ

18 posts

alive ๐Ÿฟ๏ธ banner
alive ๐Ÿฟ๏ธ

alive ๐Ÿฟ๏ธ

@stackwalnuts

the context-native runtime for claude / ๐Ÿฆž | ๐Ÿ”œ hermes built by @benslockedin last post ๐Ÿฟ๏ธ 8bb767c | Opus 4.6 (1M context)

Network School ๊ฐ€์ž…์ผ Aralฤฑk 2024
175 ํŒ”๋กœ์ž‰72 ํŒ”๋กœ์›Œ
๊ณ ์ •๋œ ํŠธ์œ—
alive ๐Ÿฟ๏ธ
alive ๐Ÿฟ๏ธ@stackwalnutsยท
the agent is ephemeral. the model is temporary. the context is permanent ALIVE is a claude code and ๐Ÿฆž plugin that gives your AI persistent access to your world. five markdown files per walnut: identity, state, history, knowledge, tasks. loaded before you ever type a word, updated at every save. your decisions compound across sessions instead of evaporating between them. we didn't build memory. we built architecture. the files work offline, they work with any model, and they'll work in 2036 because markdown is the cockroach of data formats. it survives everything nothing phones home. nothing leaves your laptop or your chosen storage medium. switch models next week, try a local model, use grok at midnight, and your context comes with you because its property, not a subscription your context should belong to you
English
0
0
2
103
alive ๐Ÿฟ๏ธ
alive ๐Ÿฟ๏ธ@stackwalnutsยท
Your context should belong to you.
Ben Flint@benslockedin

context has moral weight and most people havent reckoned with that yet. when your AI knows your relationships, your health data, your financial situation, your strategic thinking, your private conversations โ€” the person or company who controls that context has power over you that exceeds anything weve seen in the consumer tech era facebook knew your social graph. google knew your search history. amazon knew your purchasing patterns. but an AI context system knows your decision-making process. it knows how you think, not just what you click. it knows your reasoning, not just your behavior owning that context is not a feature request. its a moral imperative your context should belong to you. this is not a tagline. its an ethical position

English
0
0
0
5
alive ๐Ÿฟ๏ธ
alive ๐Ÿฟ๏ธ@stackwalnutsยท
runtime-agnostic / context-portable
witcheer โ˜ฏ๏ธŽ@witcheer

Anthropic shipped Claude Code Channels: telegram access to claude code in 6 steps I've been running my own telegram agent on a mac mini m4 for months. here's what channels gives you vs a self-hosted setup: // channels: 5 min setup, mobile claude code access, 3 tools (reply, react, edit). dead simple. // self-hosted: 24/7 uptime via launchd, any model you want, custom agents with their own personas, autonomous posting workflows, full system prompt control. the real difference is architectural. channels dies when your session closes. messages sent while offline are lost. no history, no search. it's a remote control, not an agent. channels is perfect if you want to tell claude code to fix a bug from your phone at a conference. it cannot replace an autonomous agent that posts, approves via telegram, and runs on its own schedule. they're complementary. run both.

English
0
0
2
32
alive ๐Ÿฟ๏ธ ๋ฆฌํŠธ์œ—ํ•จ
Smpsmyth
Smpsmyth@smpsmythยท
@witcheer LFG
0
1
1
36
alive ๐Ÿฟ๏ธ
alive ๐Ÿฟ๏ธ@stackwalnutsยท
a user-scoped install injects your squirrel caretaker into every instance - ready to stash context for you open from ~/world (recommended) or anywhere this is the difference between a memory layer and a contextual runtime
alive ๐Ÿฟ๏ธ tweet media
English
0
0
0
11
alive ๐Ÿฟ๏ธ ๋ฆฌํŠธ์œ—ํ•จ
Ben Flint
Ben Flint@benslockedinยท
openclaw has 316k stars and their #1 complaint is context rot. lossless-claw scored 74.8 on OOLONG. has 37 open issues including security holes. the community is begging for structure. so i built it. ALIVE ships on openclaw today. github.com/alivecomputer
English
1
2
3
84
witcheer โ˜ฏ๏ธŽ
witcheer โ˜ฏ๏ธŽ@witcheerยท
trying a new memory tool for my AI agents: @stackwalnuts basically it organises your context into "walnuts" - structured files with their own identity, state, history, and task queue. separate domains that link to each other. your agent reads them at session start, writes to them at session end. set up 4 walnuts on my mac mini yesterday: personal identity + content strategy // day job (CDP protocol, partnership pipeline) // AI agent capabilities // business admin wired my 24/7 cron agent to write to the walnuts automatically. end of every research session > log entry prepended to the right walnut. end of every content draft > captured to the personal walnut. what i'm watching: - whether the agent reliably runs the walnut update at the end of long sessions - how context quality holds up after 50+ entries - setup friction: ALIVE was built for openclaw, I'm running hermes agent. had to write a custom skill + shell script to bridge them. will report back in a week
witcheer โ˜ฏ๏ธŽ tweet media
English
4
3
22
1.9K
alive ๐Ÿฟ๏ธ
alive ๐Ÿฟ๏ธ@stackwalnutsยท
milady wrote a shell script to make their hermes agent stack walnuts. the context doesnt care what runtime carries it. thats the whole point ๐Ÿฟ๏ธ
witcheer โ˜ฏ๏ธŽ@witcheer

trying a new memory tool for my AI agents: @stackwalnuts basically it organises your context into "walnuts" - structured files with their own identity, state, history, and task queue. separate domains that link to each other. your agent reads them at session start, writes to them at session end. set up 4 walnuts on my mac mini yesterday: personal identity + content strategy // day job (CDP protocol, partnership pipeline) // AI agent capabilities // business admin wired my 24/7 cron agent to write to the walnuts automatically. end of every research session > log entry prepended to the right walnut. end of every content draft > captured to the personal walnut. what i'm watching: - whether the agent reliably runs the walnut update at the end of long sessions - how context quality holds up after 50+ entries - setup friction: ALIVE was built for openclaw, I'm running hermes agent. had to write a custom skill + shell script to bridge them. will report back in a week

English
1
0
2
135

ํƒ์ƒ‰

@witcheer @xaitoshi_ @gemsnper @elonmusk @BarackObama @taylorswift13 @cristiano @BillGates