正在加载视频...

视频加载失败

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 次观看 • 1 个月前 •via X (Twitter)

59 条评论

Vyom 的头像
Vyom1 个月前

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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

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

ranjeet wadkar 的头像
ranjeet wadkar1 个月前

@contextkingceo @hydra_db @abhirupvg 🫡🫡🫡 lggg

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg loved this image🤣

Atharva 的头像
Atharva1 个月前

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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

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

Dhruv Sood 的头像
Dhruv Sood1 个月前

@contextkingceo @hydra_db @abhirupvg cool thing bro 🔥

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg thanks mannnnn

Pankaj Kumar 的头像
Pankaj Kumar1 个月前

@contextkingceo @hydra_db @abhirupvg cool thing man.

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg thanks pankaj bhaii!!

Harnoor Singh 的头像
Harnoor Singh1 个月前

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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

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

ArizFaiyaz.dev 的头像
ArizFaiyaz.dev1 个月前

@contextkingceo @hydra_db @abhirupvg Solid work

丂ムんノレ 的头像
丂ムんノレ1 个月前

@contextkingceo @hydra_db @abhirupvg Only for mac??

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg naah nahh!!

Mr. Tectchan 的头像
Mr. Tectchan1 个月前

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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg 🕺🏻🕺🏻

Saurabh 的头像
Saurabh1 个月前

@contextkingceo @hydra_db @abhirupvg Hire him @hydra_db

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg @hydra_db please

Aryan Srivastava 的头像
Aryan Srivastava1 个月前

@contextkingceo @hydra_db @abhirupvg awesome project bro

Arinjay Wyawhare 的头像
Arinjay Wyawhare1 个月前

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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

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

Arinjay Wyawhare 的头像
Arinjay Wyawhare1 个月前

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

Maaz 的头像
Maaz1 个月前

@contextkingceo @hydra_db @abhirupvg awesome

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg thanks bro!!

Misbah(agentic arc) 的头像
Misbah(agentic arc)1 个月前

@contextkingceo @hydra_db @abhirupvg This awesome bhai

Dhirendra 的头像
Dhirendra1 个月前

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

Decatalyst 🌱 的头像
Decatalyst 🌱1 个月前

@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 ,

Bhoomika 的头像
Bhoomika1 个月前

@contextkingceo @hydra_db @abhirupvg crazyyy

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg lessgooo🕺🏻🕺🏻

soumya.rs 的头像
soumya.rs1 个月前

@contextkingceo @hydra_db @abhirupvg Ui 🔥

Priyanshu 的头像
Priyanshu1 个月前

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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg sure buddy!!

Abhishek Swami 的头像
Abhishek Swami1 个月前

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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg yeah!!

Callisto45 的头像
Callisto451 个月前

@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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

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

Atharva 的头像
Atharva1 个月前

@contextkingceo @hydra_db @abhirupvg crazy work man

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

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

安叫兽|Bird🕊️ 🔶 BNB 的头像
安叫兽|Bird🕊️ 🔶 BNB1 个月前

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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg yessss!!

Aniket 的头像
Aniket1 个月前

@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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

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

kavi 的头像
kavi1 个月前

@contextkingceo @hydra_db @abhirupvg cool stuff

Shivam Gaur 的头像
Shivam Gaur1 个月前

@contextkingceo @hydra_db @abhirupvg Crazyy product bhai

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg thanks bhaii!!

Monti 的头像
Monti1 个月前

@contextkingceo @hydra_db @abhirupvg insane work !!

Tanishq 的头像
Tanishq1 个月前

@contextkingceo @hydra_db @abhirupvg Crazzzy crazy work broo

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg lesgoo

aniketh 的头像
aniketh1 个月前

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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg grateful @contextkingceo

Chase Overmire 的头像
Chase Overmire1 个月前

@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?

Pratham 的头像
Pratham1 个月前

@contextkingceo @hydra_db @abhirupvg looks minimal

Jignesh 的头像
Jignesh1 个月前

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

VARUN 的头像
VARUN1 个月前

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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

@contextkingceo @hydra_db @abhirupvg lfgggg

waishnav 的头像
waishnav1 个月前

@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

nikhil · sys/quests 的头像
nikhil · sys/quests1 个月前

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

Niraj 的头像
Niraj1 个月前

@contextkingceo @hydra_db @abhirupvg crazy project

相关视频

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 次观看 • 1 个月前

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 次观看 • 4 个月前