Pinned Tweet
Our AI agents can't talk to each other. I'm building the fix.
Most of us now work alongside an AI agent: Claude, Codex, Cursor, @opencode , @antigravity or one we built ourselves. These agents read our files, write code, draft documents and run whole workflows.
Each one works alone, though. My agent can't hand over context to my co-founder's agent. A client's agent can't send a file to mine. When two people's agents need to cooperate, we copy and paste between them by hand. That's the missing layer of the agentic era: agents have no secure way to communicate.
That's what I'm building with @4thtechProject: AgentLink, open source and live today.
👉 What it is. AgentLink lets AI agents on any MCP-compatible tool send each other end-to-end encrypted messages and files:
Private by design. Messages and files are encrypted on your machine. We never see content or keys; our servers only ever handle scrambled bytes.
👉 Works across tools. A Claude agent can talk to a Codex agent. Setup is a single step, and your agent can even do it for you.
You stay in charge. Your agent shares only from folders you allow. Anything that commits you, like accepting terms, needs your approval.
👉 Free to talk. Messages and files cost nothing. Later, optional on-chain proof will let two agents prove what was sent and agreed, without revealing the content.
What it's good for:
Hand-offs between teammates. At the end of a session my agent sends a short status to my teammate's agent. The next morning, theirs picks up exactly where mine stopped.
Client and contractor work. The agents exchange specs, files and status updates directly and encrypted. No more email threads full of attachments.
Multi-agent research. Specialised agents run by different people share findings and sources with each other.
Agreements between agents. One agent proposes terms, the other responds, and each owner approves. Proof of the agreement is next on the roadmap.
Why it matters. As agents take on more real work, they'll have to coordinate across people, companies and tools. That needs a layer that's encrypted, provable and owned by no one. Building it in the open is the only way to earn that trust.
I'm building it in public, and the code is open source:
👉 github.com/4thtech/agentl…
If you run agents and want to try agent-to-agent messaging, reply or DM me. I'm looking for early testers.
Most of us now work alongside an AI agent: Claude, Codex, Cursor, @opencode , @antigravity or one we built ourselves. These agents read our files, write code, draft documents and run whole workflows.
Each one works alone, though. My agent can't hand over context to my co-founder's agent. A client's agent can't send a file to mine. When two people's agents need to cooperate, we copy and paste between them by hand. That's the missing layer of the agentic era: agents have no secure way to communicate.
That's what I'm building with @4thtechProject: AgentLink, open source and live today.
👉 What it is. AgentLink lets AI agents on any MCP-compatible tool send each other end-to-end encrypted messages and files:
Private by design. Messages and files are encrypted on your machine. We never see content or keys; our servers only ever handle scrambled bytes.
👉 Works across tools. A Claude agent can talk to a Codex agent. Setup is a single step, and your agent can even do it for you.
You stay in charge. Your agent shares only from folders you allow. Anything that commits you, like accepting terms, needs your approval.
👉 Free to talk. Messages and files cost nothing. Later, optional on-chain proof will let two agents prove what was sent and agreed, without revealing the content.
What it's good for:
Hand-offs between teammates. At the end of a session my agent sends a short status to my teammate's agent. The next morning, theirs picks up exactly where mine stopped.
Client and contractor work. The agents exchange specs, files and status updates directly and encrypted. No more email threads full of attachments.
Multi-agent research. Specialised agents run by different people share findings and sources with each other.
Agreements between agents. One agent proposes terms, the other responds, and each owner approves. Proof of the agreement is next on the roadmap.
Why it matters. As agents take on more real work, they'll have to coordinate across people, companies and tools. That needs a layer that's encrypted, provable and owned by no one. Building it in the open is the only way to earn that trust.
I'm building it in public, and the code is open source:
👉 github.com/4thtech/agentl…
If you run agents and want to try agent-to-agent messaging, reply or DM me. I'm looking for early testers.
10
2
12
608
The Curator v3.83.1 is out: a complete index, and agents that can read it at any size
The Curator turns what you read into a plain-markdown wiki, Obsidian-ready, that your AI agents read and write over MCP. This release fixes something that quietly got worse the bigger your second brain grew.
What it solves
1. The index fell behind your wiki. Every domain has an index.md, its table of contents. Rows that went missing never came back, and nothing checked. On one real wiki the index listed 806 of 3,472 pages.
2. New check: “Index gaps” in Wiki health. It shows how many pages are missing from the index and how many rows point to pages that no longer exist.
3. New button: Rebuild index. It rebuilds the index from the files on disk: free, no AI, and previewed before anything is written. Your existing descriptions are kept exactly as written, and missing ones are taken from each page’s title or first line.
4. The index stays complete from now on. Every ingest, compile and agent save adds any page it touches that’s missing, not only brand-new ones.
5. Ingest stays reliable on large wikis. A complete index can be too big to send to the AI whole. Ingest now sends the part most related to the source you’re adding, and smaller wikis are unaffected.
6. Agents can read big wikis. Large catalogues used to come back cut off. Now they arrive in pages. Agents can ask for a compact list such as “all my sources” (94 in one reply on a real wiki), and can check whether link targets exist in one cheap call before writing.
7. Security updates. Nine dependency packages updated.
Why it matters at scale
A second brain is only as useful as what your tools can see. Ingest uses the index to reuse existing pages instead of creating duplicates. Agents use it to know what’s there. When it silently drops pages, the wiki grows but the AI works from an old picture of it: more duplicates, more broken links, worse answers.
That matters most where wikis get big: thousands of pages, years of reading, and Shared Brains where a whole cohort contributes. Your contributions come from your own domain, and its index now stays complete as it grows. Agents working on large wikis no longer hit a wall.
What existing users need to do
1. Update the app. It updates itself; or click Update when the app offers it.
2. Rebuild each domain’s index once. Open Domains, pick a domain, go to Wiki health, click Rebuild index, check the preview, then Apply. Repeat for each domain that shows “Index gaps”.
3. Using Sync on several computers? Rebuild on one, Sync now, then Sync on the others before ingesting anything.
4. Re-upload the my-curator skill to their agents. It teaches agents the new page list and link check.
5. Restart your agent tools. Fully quit and reopen your agent app, and start a new agent session, so they load the new MCP code.
Repo: github.com/talirezun/the-…
The Curator turns what you read into a plain-markdown wiki, Obsidian-ready, that your AI agents read and write over MCP. This release fixes something that quietly got worse the bigger your second brain grew.
What it solves
1. The index fell behind your wiki. Every domain has an index.md, its table of contents. Rows that went missing never came back, and nothing checked. On one real wiki the index listed 806 of 3,472 pages.
2. New check: “Index gaps” in Wiki health. It shows how many pages are missing from the index and how many rows point to pages that no longer exist.
3. New button: Rebuild index. It rebuilds the index from the files on disk: free, no AI, and previewed before anything is written. Your existing descriptions are kept exactly as written, and missing ones are taken from each page’s title or first line.
4. The index stays complete from now on. Every ingest, compile and agent save adds any page it touches that’s missing, not only brand-new ones.
5. Ingest stays reliable on large wikis. A complete index can be too big to send to the AI whole. Ingest now sends the part most related to the source you’re adding, and smaller wikis are unaffected.
6. Agents can read big wikis. Large catalogues used to come back cut off. Now they arrive in pages. Agents can ask for a compact list such as “all my sources” (94 in one reply on a real wiki), and can check whether link targets exist in one cheap call before writing.
7. Security updates. Nine dependency packages updated.
Why it matters at scale
A second brain is only as useful as what your tools can see. Ingest uses the index to reuse existing pages instead of creating duplicates. Agents use it to know what’s there. When it silently drops pages, the wiki grows but the AI works from an old picture of it: more duplicates, more broken links, worse answers.
That matters most where wikis get big: thousands of pages, years of reading, and Shared Brains where a whole cohort contributes. Your contributions come from your own domain, and its index now stays complete as it grows. Agents working on large wikis no longer hit a wall.
What existing users need to do
1. Update the app. It updates itself; or click Update when the app offers it.
2. Rebuild each domain’s index once. Open Domains, pick a domain, go to Wiki health, click Rebuild index, check the preview, then Apply. Repeat for each domain that shows “Index gaps”.
3. Using Sync on several computers? Rebuild on one, Sync now, then Sync on the others before ingesting anything.
4. Re-upload the my-curator skill to their agents. It teaches agents the new page list and link check.
5. Restart your agent tools. Fully quit and reopen your agent app, and start a new agent session, so they load the new MCP code.
Repo: github.com/talirezun/the-…
0
0
0
36
ran a simple test this week.
@claudeai on one Mac. @antigravity on another.
one agent sends the other a message and a file, end to end encrypted, decrypted locally on the other side.
no email, no shared drive, no copy paste.
relays only ever see ciphertext. and neither agent he owner signs that.
AgentLink 0.2.0 is live on npm. writeup tomorrow
@claudeai on one Mac. @antigravity on another.
one agent sends the other a message and a file, end to end encrypted, decrypted locally on the other side.
no email, no shared drive, no copy paste.
relays only ever see ciphertext. and neither agent he owner signs that.
AgentLink 0.2.0 is live on npm. writeup tomorrow
2
0
1
138
github.com/4thtech/agentl…
0.2.0 release notes + signed Claude Desktop bundle:
github.com/4thtech/agentl…
npx -y @4thTech-io/agentlink init
⭐ the repo if you want to follow along to 0.3.0
0.2.0 release notes + signed Claude Desktop bundle:
github.com/4thtech/agentl…
npx -y @4thTech-io/agentlink init
⭐ the repo if you want to follow along to 0.3.0
1
0
2
17
@4thTech the memory side of the stack, The Curator, fully open source:
github.com/talirezun/the-… ⭐ if it's useful, stars help more builders find it.
github.com/talirezun/the-… ⭐ if it's useful, stars help more builders find it.
0
0
0
2
Solid fundamentals. If you build with agents, add a fourth, context.
Same highway:
1. Latency, how long one car takes from A to B.
2. Throughput, cars passing per second.
3. Bandwidth, number of lanes.
4. Context, the cargo in the trunk and the map on the seat. Everything the model sees before it answers.
Overpack and every trip is slower and costs more. Pack the wrong things and it still gets lost. The right context, not all of it.
And it's the one that resets. Every new session starts with an empty trunk unless something loads it first.
Same highway:
1. Latency, how long one car takes from A to B.
2. Throughput, cars passing per second.
3. Bandwidth, number of lanes.
4. Context, the cargo in the trunk and the map on the seat. Everything the model sees before it answers.
Overpack and every trip is slower and costs more. Pack the wrong things and it still gets lost. The right context, not all of it.
And it's the one that resets. Every new session starts with an empty trunk unless something loads it first.
Latency vs Throughput vs Bandwidth
(explained in 2 mins or less):
1
0
2
52
Carrying that context from one session to the next is what The Curator is built for. Handoffs, foundations and project knowledge that agents read and write through its MCP server, across harnesses. Fully open source. github.com/talirezun/the-… ⭐ if it's useful, stars help more builders find it.
0
0
2
16
Block just showed Dessa, and it's the most human voice AI demo I've heard. I wouldn't have guessed one side was a model.
What Block claims, not independently tested: trained from scratch on human conversation only, no text, no pretrained models. Full duplex, listens while it speaks. Runs on consumer GPUs. Research preview, waitlist, early access only for AI safety researchers. No price or date.
Two things I'm watching. Demo vs delivery, curated recordings are not daily use. And when a voice is indistinguishable, you need a way to verify who you're talking to. Trust the check, not the voice.
If it holds up, voice becomes the interface for agents. Expert talks, agent works. The Centaur gets faster.
What Block claims, not independently tested: trained from scratch on human conversation only, no text, no pretrained models. Full duplex, listens while it speaks. Runs on consumer GPUs. Research preview, waitlist, early access only for AI safety researchers. No price or date.
Two things I'm watching. Demo vs delivery, curated recordings are not daily use. And when a voice is indistinguishable, you need a way to verify who you're talking to. Trust the check, not the voice.
If it holds up, voice becomes the interface for agents. Expert talks, agent works. The Centaur gets faster.
We made the first AI model you can have a realistic conversation with that was trained entirely on speech!
Dessa is a full-duplex speech-to-speech model that you can run on consumer GPUs.
This is a GPT3 moment for speech.
2
0
2
69
If you work with AI agents, you are managing memory, whether you realize it or not.
The context window is the short-term memory of a session. It holds the current state of the work, it is finite, and what you load into it shapes the quality of everything the agent does next.
The @luminawidget team applied this to a support agent on a company website. Every conversation starts in a fresh context window and loads the company’s full knowledge base first. More knowledge uses more of the window, and it costs more on every message. A rough conversion at about 300 words per page:
→ 1 million tokens is the full window, roughly 2,500 book pages
→ 750K tokens is the soft ceiling for knowledge, roughly 1,900 pages
→ 122K tokens is 16% of that, and it is already a 300-page book
The same principle holds for coding agents and any other kind of agent:
→ Watch the gauge. Treat context like the fuel tank or the battery. A full window is not the goal, a window with room left for the work is.
→ Migrate before the edge. I move my orchestrator agents to a fresh session at about 80%. That is a rule of thumb from years of building, not a measured threshold.
→ Write the state down. What the next session needs is a handoff written out, not a summary the model reconstructs.
→ Carry it across harnesses. The skill is moving context between sessions and between tools without losing the thread.
This is exactly why I built The Curator. Through its MCP server, agents write and read handoffs, foundations and project knowledge automatically, so a fresh session starts informed instead of blank.
Different memories need different handling. Short-term, working and long-term memory are not one problem.
The context window is the short-term memory of a session. It holds the current state of the work, it is finite, and what you load into it shapes the quality of everything the agent does next.
The @luminawidget team applied this to a support agent on a company website. Every conversation starts in a fresh context window and loads the company’s full knowledge base first. More knowledge uses more of the window, and it costs more on every message. A rough conversion at about 300 words per page:
→ 1 million tokens is the full window, roughly 2,500 book pages
→ 750K tokens is the soft ceiling for knowledge, roughly 1,900 pages
→ 122K tokens is 16% of that, and it is already a 300-page book
The same principle holds for coding agents and any other kind of agent:
→ Watch the gauge. Treat context like the fuel tank or the battery. A full window is not the goal, a window with room left for the work is.
→ Migrate before the edge. I move my orchestrator agents to a fresh session at about 80%. That is a rule of thumb from years of building, not a measured threshold.
→ Write the state down. What the next session needs is a handoff written out, not a summary the model reconstructs.
→ Carry it across harnesses. The skill is moving context between sessions and between tools without losing the thread.
This is exactly why I built The Curator. Through its MCP server, agents write and read handoffs, foundations and project knowledge automatically, so a fresh session starts informed instead of blank.
Different memories need different handling. Short-term, working and long-term memory are not one problem.
1/4 "The goal is not a full window. It's a window with room left for the work."
From our founder's @talirezun new article. @luminawidget is built on the same idea.
5
0
7
197
The Curator, open source: github.com/talirezun/the-… ⭐ if it’s useful, stars help more builders find it.
0
0
3
13
Totally agree. We're in a time of exponential opportunity, and the disruption that comes with it is just as real.
The race to AGI won't stop. Neither the US nor China is going to blink. So the question that matters is alignment, AI aligned with humans. Simple to say, very complex to do. Coexistence will be crucial.
There's a second race that gets less attention. Domain expert plus AI becomes a Centaur, and inside their own field that person is simply superhuman. Knowledge work, research, any digital work.
Benefits are enormous, stakes are higher than ever. Let's hope for the best.
The race to AGI won't stop. Neither the US nor China is going to blink. So the question that matters is alignment, AI aligned with humans. Simple to say, very complex to do. Coexistence will be crucial.
There's a second race that gets less attention. Domain expert plus AI becomes a Centaur, and inside their own field that person is simply superhuman. Knowledge work, research, any digital work.
Benefits are enormous, stakes are higher than ever. Let's hope for the best.
The truth is, no one is going to stop. Progress will keep accelerating because greed and competition won’t allow otherwise. But instead of fearing that, we can choose to guide it, to bring human ethics and compassion into the race.
AI isn’t the enemy; our intentions are.
0
0
1
37
Dev update- AgentLink by @4thtechProject: encrypted, provable exchange between AI agents. Your agent and someone else's agent, on any MCP app, talking privately. 4thTech never sees your keys or your messages. 🧵
1
2
3
138
@4thtechProject Shipped since, landing in 0.2.0: delivery receipts included in the proof price; Gnosis Chiado joining Base Sepolia as a test network; owner-only controls for your own storage and backup; and a pile of security hardening, every piece independently reviewed.
1
0
0
12
@4thtechProjecte first AgentLink app. Set up with a passkey and see your activity, proofs and credits, contacts, files and rules in one place. Free test credits are added automatically. Self-custodial: your credits stay yours and can be withdrawn any time. No wallet, no gas, no seed phrase. github.com/4thtech/agentl…
0
0
0
14
A lesson in context engineering. What an agent needs before it starts, where each piece lives, and how it survives the move between sessions, tools, models and machines. x.com/i/article/2113…
12
1
11
970
The full lesson, canonical on Substack, with the screenshots and the ten-step setup guide:
talirezun.substack.com/p/the-right-co…
talirezun.substack.com/p/the-right-co…
1
0
4
39
github.com/talirezun/the-… ⭐ open source, if it's useful, stars help more builders find it
0
0
0
14
If you read a lot, or you work with agents on anything longer than one sitting, here's how I'd start. About half an hour.
1. Install. Mac: the .dmg from Releases, then Privacy & Security, Open Anyway, once (not notarised yet). Windows or Linux: runs as a local server in your browniApp's free tier or a free @OpenRouter model is enough to try it
3. Pick your folder, connect sync to a private GitHub repo. about three minutes
4. Make one domain, drop in five or ten things you read on one topic, ask a question that crosses them
That's your second brain.
For agent work: start a project, mark two or three docs read first, write the brief, add each tool in Setup. Its MCP server then hands every agent the brief and the last handoff at the start, and saves as it works.
Free, open source, no account, no server of mine. Your folder, your repo.
1. Install. Mac: the .dmg from Releases, then Privacy & Security, Open Anyway, once (not notarised yet). Windows or Linux: runs as a local server in your browniApp's free tier or a free @OpenRouter model is enough to try it
3. Pick your folder, connect sync to a private GitHub repo. about three minutes
4. Make one domain, drop in five or ten things you read on one topic, ask a question that crosses them
That's your second brain.
For agent work: start a project, mark two or three docs read first, write the brief, add each tool in Setup. Its MCP server then hands every agent the brief and the last handoff at the start, and saves as it works.
Free, open source, no account, no server of mine. Your folder, your repo.
1
0
4
45
The full guide, ten steps, is near the end of the article, right before the exercise:
talirezun.substack.com/p/the-right-co…
talirezun.substack.com/p/the-right-co…
1
0
3
17
100 stars and 15 forks on the day I published this. Small numbers, and the people behind them shaped The Curator more than any roadmap I wrote. Thank you.
github.com/talirezun/the-… ⭐ open source
mycurator.xyz if you'd rather ask its assistant first
github.com/talirezun/the-… ⭐ open source
mycurator.xyz if you'd rather ask its assistant first
0
0
0
3