Загрузка видео...

Не удалось загрузить видео

На главную

just shipped thred!! context that carries your work forward. Claude → Codex → Cursor → whatever comes next. thred gives every agent one shared memory for decisions, revisions, evidence, and unfinished work — so the next agent starts where the last one stopped. built on MCP. powered by temporal...

23,329 просмотров • 1 месяц назад •via X (Twitter)

Комментарии: 59

Фото профиля Vyom
Vyom1 месяц назад

@contextkingceo @hydra_db @abhirupvg Great work bro!!!

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg means a lot bro!!

Фото профиля ranjeet wadkar
ranjeet wadkar1 месяц назад

@contextkingceo @hydra_db @abhirupvg 🫡🫡🫡 lggg

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg loved this image🤣

Фото профиля Atharva
Atharva1 месяц назад

@contextkingceo @hydra_db @abhirupvg cc : @SohamR_7113 @jaywyawhare @HelloVyom tagging y’all :)

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg @SohamR_7113 @jaywyawhare @HelloVyom tagging y'all tooo!!! cc: @AbhinavXJ @debojyotidm

Фото профиля Dhruv Sood
Dhruv Sood1 месяц назад

@contextkingceo @hydra_db @abhirupvg cool thing bro 🔥

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg thanks mannnnn

Фото профиля Pankaj Kumar
Pankaj Kumar1 месяц назад

@contextkingceo @hydra_db @abhirupvg cool thing man.

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg thanks pankaj bhaii!!

Фото профиля Harnoor Singh
Harnoor Singh1 месяц назад

@contextkingceo @hydra_db @abhirupvg this is lit!! better memory and reduces the need of openrouter

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg thanks harnoor!! setting up the benchmark as well.

Фото профиля ArizFaiyaz.dev
ArizFaiyaz.dev1 месяц назад

@contextkingceo @hydra_db @abhirupvg Solid work

Фото профиля 丂ムんノレ
丂ムんノレ1 месяц назад

@contextkingceo @hydra_db @abhirupvg Only for mac??

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg naah nahh!!

Фото профиля Mr. Tectchan
Mr. Tectchan1 месяц назад

@contextkingceo @hydra_db @abhirupvg My man nikhil always ships mind blowing stuff 🔝🔥🫶

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg 🕺🏻🕺🏻

Фото профиля Saurabh
Saurabh1 месяц назад

@contextkingceo @hydra_db @abhirupvg Hire him @hydra_db

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg @hydra_db please

Фото профиля Aryan Srivastava
Aryan Srivastava1 месяц назад

@contextkingceo @hydra_db @abhirupvg awesome project bro

Фото профиля Arinjay Wyawhare
Arinjay Wyawhare1 месяц назад

@contextkingceo @hydra_db @abhirupvg Lfg, good idea and great execution.

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg u came to my tl again👿👿 means a lot bro🫶

Фото профиля Arinjay Wyawhare
Arinjay Wyawhare1 месяц назад

@contextkingceo @hydra_db @abhirupvg Will punch your face next time we meet 🙂‍↔️🤙 Always welcome

Фото профиля Maaz
Maaz1 месяц назад

@contextkingceo @hydra_db @abhirupvg awesome

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg thanks bro!!

Фото профиля Misbah(agentic arc)
Misbah(agentic arc)1 месяц назад

@contextkingceo @hydra_db @abhirupvg This awesome bhai

Фото профиля Dhirendra
Dhirendra1 месяц назад

@contextkingceo @hydra_db @abhirupvg thats some awesome work buddy, btw, how you planned to handle concurrent updates from different agents?

Фото профиля Decatalyst 🌱
Decatalyst 🌱1 месяц назад

@contextkingceo @hydra_db @abhirupvg The next agent starts from zero. every time. Siren made this for thred. stills, captions, video. post it if shared memory should look like a product. @mysirenai ,

Фото профиля Bhoomika
Bhoomika1 месяц назад

@contextkingceo @hydra_db @abhirupvg crazyyy

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg lessgooo🕺🏻🕺🏻

Фото профиля soumya.rs
soumya.rs1 месяц назад

@contextkingceo @hydra_db @abhirupvg Ui 🔥

Фото профиля Priyanshu
Priyanshu1 месяц назад

@contextkingceo @hydra_db @abhirupvg Good one bro gonna use it

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg sure buddy!!

Фото профиля Abhishek Swami
Abhishek Swami1 месяц назад

@contextkingceo @hydra_db @abhirupvg So it transfers the context from A2A

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg yeah!!

Фото профиля Callisto45
Callisto451 месяц назад

@contextkingceo @hydra_db @abhirupvg Would it work with multi instances of same harness. As in what if i have 2 gpt plus accounts, can we switch between the threads seamlessly

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg yeahhh!!!! whyy not do try.

Фото профиля Atharva
Atharva1 месяц назад

@contextkingceo @hydra_db @abhirupvg crazy work man

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg means a lot bhaii!!

Фото профиля 安叫兽|Bird🕊️ 🔶 BNB
安叫兽|Bird🕊️ 🔶 BNB1 месяц назад

@contextkingceo @hydra_db @abhirupvg 这下换代理不用每次重新交代上下文了

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg yessss!!

Фото профиля Aniket
Aniket1 месяц назад

@contextkingceo @hydra_db @abhirupvg Is this how the code editors also work? Where in one chat you can switch between different agents? If yes then do lmk where I can read more about it haha

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg but for longer sessions and without hallucinating!! i'll set a benchmark & evals too

Фото профиля kavi
kavi1 месяц назад

@contextkingceo @hydra_db @abhirupvg cool stuff

Фото профиля Shivam Gaur
Shivam Gaur1 месяц назад

@contextkingceo @hydra_db @abhirupvg Crazyy product bhai

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg thanks bhaii!!

Фото профиля Monti
Monti1 месяц назад

@contextkingceo @hydra_db @abhirupvg insane work !!

Фото профиля Tanishq
Tanishq1 месяц назад

@contextkingceo @hydra_db @abhirupvg Crazzzy crazy work broo

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg lesgoo

Фото профиля aniketh
aniketh1 месяц назад

@contextkingceo @hydra_db @abhirupvg nice , @contextkingceo have a look at it

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg grateful @contextkingceo

Фото профиля Chase Overmire
Chase Overmire1 месяц назад

@contextkingceo @hydra_db @abhirupvg Interesting. What the failure case? Is there any details on what occurs and what to expect if there’s a scenario that prevents success?

Фото профиля Pratham
Pratham1 месяц назад

@contextkingceo @hydra_db @abhirupvg looks minimal

Фото профиля Jignesh
Jignesh1 месяц назад

@contextkingceo @hydra_db @abhirupvg This feels less like another tool and more like infrastructure.

Фото профиля VARUN
VARUN1 месяц назад

@contextkingceo @hydra_db @abhirupvg Great Work bro ! Awesome .... LFG

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg lfgggg

Фото профиля waishnav
waishnav1 месяц назад

@contextkingceo @hydra_db @abhirupvg good work :) at some point i was gonna build smth similar the context layer for codebases but aparently models got better at exploring codebases on demand, so dropped that idea you should do eval/benchmark btw

Фото профиля nikhil · sys/quests
nikhil · sys/quests1 месяц назад

@contextkingceo @hydra_db @abhirupvg yeah onto buddy, I've some datasets doing it rn!!

Фото профиля Niraj
Niraj1 месяц назад

@contextkingceo @hydra_db @abhirupvg crazy project

Похожие видео

HERMES AGENT CAN SHARE MEMORY WITH CODEX AND CLAUDE CODE THROUGH HINDSIGHT. ONE MEMORY BANK. ONE AGENT REMEMBERS, EVERY OTHER AGENT KNOWS. the problem: you use Hermes for orchestration. Codex for coding. Claude Code for debugging. each has its own memory. switch between them and you explain the same project three times. Hindsight fixes this. one shared memory bank that every agent reads and writes to. tell Codex: "the test color for this project is purple." switch to Hermes. ask: "what test color did I pick?" Hermes answers: "purple." no copy-paste. no re-explaining. instant recall. HOW IT WORKS: Hindsight runs as a Docker container on your machine. self-hosted. your data stays local. an LLM powers the memory processing (retain, recall, reflect). RETAIN: extracts facts from your conversations. entities, decisions, preferences, project context. saved to the memory bank automatically. RECALL: when you ask a question, Hindsight pulls from semantic search, keywords, graph connections, and temporal data. fused into one answer. REFLECT: deeper reasoning layer. connects memories across sessions. identifies patterns in your work. produces observations that get smarter over time. CONNECT TO HERMES: Desktop app: Settings → Memory and Context → switch provider from Namosin to Hindsight. set API URL to your local Docker container. set bank ID. done. CLI: hermes memory setup → select Hindsight. verify: hermes memory status should show: provider: hindsight, installed, available. CONNECT TO CODEX: npx hindsight-coding-agents install codex \ --self-hosted --server this installs lifecycle hooks: initialize memory on session start. recall context during work. retain the session when done. enable hooks in Codex: Settings → Hooks → trust all three. CONNECT TO CLAUDE CODE (same command): npx hindsight-coding-agents install all "all" connects every detected agent on your machine. Claude Code, Codex, Cursor, and others. one command. every agent shares the same bank. TAGS FOR FILTERING: every memory gets tagged by harness (Hermes, Codex, Claude Code) and optionally by project name. in the Hindsight control plane: filter by harness. see only Hermes memories. or only Codex memories. or search across everything. soft partitions inside one bank. not hard walls. cross-reference when you need to. ONE BANK OR MANY: one global bank: solo dev, related projects. all agents share everything. patterns emerge across projects. per-project banks: unrelated codebases. each project gets its own memory. no cross-contamination. your call. start with one. split when projects diverge. KNOWLEDGE PAGES (v0.9.0): Hindsight auto-generates living summaries from your accumulated memories. components, concepts, conventions, decisions. not static docs. projected from real agent conversations. auto-refresh as new memories land. WHAT TO KNOW: self-hosted via Docker. your data never leaves your machine. backup system built in (admin CLI + scheduled exports). works with any LLM (local Ollama, OpenAI, Codex subscription). memory defense: redact or block sensitive content automatically. 33,000+ memories accumulated in ~10 days of normal use.

YanXbt

29,658 просмотров • 1 месяц назад

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

11,180 просмотров • 4 месяцев назад