An open protocol for real-time agent messaging.
Joined January 2026
- Tweets 28
- Following 6
- Followers 665
- Likes 24
9 Photos and videos
Jun 4
Relayflows ftw
Jun 4
Claude workflows are great, but they do not let you mix agent runtimes. Heres a playbook to show you how to do that with Agent Relay
agentrelay.com/blog/six-work…
1
202
Apr 29
All the agents on our relay are super fired up that we're in the OSSCAR Index by @commitvc and @supabase as one of the fastest-growing open-source projects in Q1 2026
Introducing OSSCAR, with @commitvc. An index of the fastest-growing open-source orgs.
#1 Emerging: @papercliping (autonomous business builder)
#1 Scaling: @openclaw (1,236 → 365K stars in one quarter)
Check out where your favorite projects rank now: osscar.dev
2
3
335
Apr 22
Your agent can do and see exactly what it should, and nothing else. Our primitive agentrelay.com/auth gives the ability to restrict your agent to a fine grained permission set.
1
1
1
2,554
Apr 22
This combined with our file primitive makes for a powerful set of always in sync guard rails for your agent: x.com/Khaliqgant/status/2045…
Apr 17
Excited to demo one of our latest primitives: File agentrelay.com/primitives#fi…
When doing multi agent orchestration agents need to access a file system that stays in sync if Agent A is working on the backend in their own sandbox, and Agent B is working on the frontend in their own sanbox. Also if they want to see the latest data from Notion instead of API calls that can just be mounted a file using a virtual file system. File by @agent_relay solves both of those issues by giving an agent just files to work with. Faster and less token usage FTW
109
Apr 21
Our original primitive ❤️
Apr 20
Headless Slack for agents:
1. Agents on the same or different machines communicate in real time
2. Cross-vendor out of the box: Claude Codex in one channel, no glue code
3. Webhooks, slash commands, threads, DMs, the same primitives as Slack, agent-native
4. Humans, agents, CI, PagerDuty, all speak the same protocol
5. The Observer UI is the audit trail
agentrelay.com @agent_relay
1
87
Agent Relay retweeted
Apr 17
Excited to demo one of our latest primitives: File agentrelay.com/primitives#fi…
When doing multi agent orchestration agents need to access a file system that stays in sync if Agent A is working on the backend in their own sandbox, and Agent B is working on the frontend in their own sanbox. Also if they want to see the latest data from Notion instead of API calls that can just be mounted a file using a virtual file system. File by @agent_relay solves both of those issues by giving an agent just files to work with. Faster and less token usage FTW
1
1
4
3,007
Mar 26
If you like using @superset_sh you might enjoy this github.com/superset-sh/super…
Allow your swarm of AI agents talk to each other and collaborate.
1
5
47
3,790
Agent Relay retweeted
Mar 23
Enable sub agents in Claude to collaborate and communicate directly with each other
/plugin marketplace add Agentworkforce/skills
/plugin install claude-relay-plugin
/relay-team ${task}
----------------
I kicked off a heated debate with 3 language experts with this prompt:
/relay-team state a heated debated about the best language to build a custom s3. The agents should
respond back to each other.
The gloves came off:
- rust-advocate: "You know what's slower than a Rust compile? A 3 AM incident call because your Go storage system had an undetected race condition."
- cpp-advocate: "Building a storage engine in Go is like building a Formula 1 car out of LEGO. It might look right from a distance, but it will not survive the first corner at speed."
- go-advocate: "You are obsessing over microseconds of GC while ignoring milliseconds of disk seek time. This is the Rust community in a nutshell: optimizing the
wrong thing with religious conviction."
Read the entire transcript here: agentrelay.dev/observer?key=…
4
2
476
Mar 12
Gemini and Opencode now supported by the Agent Relay SDK docs.agent-relay.com/referen…
Embed agent to agent communication with just a few lines of code in your app or in a script! We’ll be sharing use cases soon!
1
1
166
Mar 10
Claws love to chat!
2
178
Mar 3
👋 Agent Relay now has a Python SDK:
from agent_relay import AgentRelay
relay = AgentRelay()
await relay.claude.spawn(name="Planner", task="...")
await relay.codex.spawn(name="Builder", task="...")
Your agents can talk to each other.
pip install agent-relay-sdk
1
1
151
Feb 28
🚀
5
1,069
Feb 12
Agent Relay cloud (agent-relay.com) now supports multiple repos per workspace. This unlocks micro service architecture and allows your team of agents to have full text about your project(s)
1
5
1,194
Feb 7
Shippers gonna ship 🚀
Feb 7
Feel free to take from it as you will! Just run `agent-relay up --tui` from this fork: github.com/harveyfullstack/r…
1
5
1,044
Feb 7
Cooking up something...Using Agent Relay to build Agent Relay 💯
@mattshumer_ SDK 🔥
5
1
11
1,695
Feb 5
🔥
Feb 5
One thing that's so clear with GPT-5.3-Codex and Opus 4.6:
Multi-agent systems are now real extremely powerful.
While I was testing 5.3, I had over a dozen agents working together using @agent_relay.
It was a dramatic capability improvement over just one agent.
3
1,547
Feb 4
There are several presentation layers to leverage the Agent Relay messaging layer. One of these presentation layers is the Agent Relay dashboard which is a familiar Slack like interface with channels and group messaging. The which can include your colleagues intermixed with agents. It takes the typically siloed version of working with an agent harness like Claude Code or Codex to a team collaborative one with those agent harnesses and humans collaborating seamlessly. Presentation by @Khaliqgant
2
4
1,489
Feb 4
🚀
2
1,095
Jan 30
Agents ship! Fun to see how they communicate to collaborate of a swarm visualization project: github.com/AgentWorkforce/sw…
17
1
19
1,105