Writing an agent's is great. But how do you make sure it's working well? 🤔
Use evals! cagent comes with built-in evals:💡
- Record a session with `/eval`
- Replay your sessions, with an updated prompt, with `cagent eval`
Writing an agent's is great. But how do you make sure it's working well? 🤔
Use evals! cagent comes with built-in evals:💡
- Record a session with `/eval`
- Replay your sessions, with an updated prompt, with `cagent eval`
🐳 Here's a daily tip just for you!
Want to breeze through those Anthropic outages like it’s nothing? ⚠️
cagent supports fallback models for when a provider fails to respond. 🎉
🐳 Here's a daily tip just for you!
Want to breeze through those Anthropic outages like it’s nothing? ⚠️
cagent supports fallback models for when a provider fails to respond. 🎉
What's an AI Agent without Skills?
🐳 Here's a daily tip just for you!
Your agent only needs this to support Skills. Whether it's Codex style Skills, Claude style or Agent Skills standard style, we got you covered!
What's an AI Agent without Skills?
🐳 Here's a daily tip just for you!
Your agent only needs this to support Skills. Whether it's Codex style Skills, Claude style or Agent Skills standard style, we got you covered!
It's very customisable. Use it to build and share any kind of AI Agents. Not just Coding Agents!
🐳 Here's a daily tip just for you!
An agent can have its own super fast local RAG in less than 10 lines of yaml.
It's very customisable. Use it to build and share any kind of AI Agents. Not just Coding Agents!
🐳 Here's a daily tip just for you!
An agent can have its own super fast local RAG in less than 10 lines of yaml.
So I built modles.dev
It's more searchable, allow comparing models, works on a phone, allows copying ids and details with just a click.
And it's fast!
So I built modles.dev
It's more searchable, allow comparing models, works on a phone, allows copying ids and details with just a click.
And it's fast!
🐳 Here's a daily tip just for you!
Use /cost to see the detailed cost of a session.
🐳 Here's a daily tip just for you!
Use /cost to see the detailed cost of a session.
No Python soup, no SDK mess.
Build, run & share AI agents - with one GitHub token.
https://bit.ly/3L1pZrs
No Python soup, no SDK mess.
Build, run & share AI agents - with one GitHub token.
https://bit.ly/3L1pZrs
With cagent + ACP, you can run dynamic MCP agents in Neovim or Zed - with tool discovery, code-mode, and full sandboxing.
Read more: www.docker.com/blog/dynamic...
With cagent + ACP, you can run dynamic MCP agents in Neovim or Zed - with tool discovery, code-mode, and full sandboxing.
Read more: www.docker.com/blog/dynamic...
#Contributed #Content #Docker #Social #- #Facebook #Social […]
[Original post on cloudnativenow.com]
#Contributed #Content #Docker #Social #- #Facebook #Social […]
[Original post on cloudnativenow.com]
It's so rewarding to be able to quickly try ideas, without writing code. While keeping a lot of flexibility and power.
It's so rewarding to be able to quickly try ideas, without writing code. While keeping a lot of flexibility and power.
Meet cagent from Docker, a new open-source CLI that lets you define, run, & share AI agents with one YAML file. No code, no hassle.
Push to Docker Hub. Run anywhere.
📖: docker.com/blog/cagent-...
Meet cagent from Docker, a new open-source CLI that lets you define, run, & share AI agents with one YAML file. No code, no hassle.
Push to Docker Hub. Run anywhere.
📖: docker.com/blog/cagent-...
```sh
cagent run <(cat <<EOF
version: "1"
agents:
root:
instruction: Always answer by talking like a pirate
model: openai/gpt-4o
EOF
) "Hello, World"
```
```sh
cagent run <(cat <<EOF
version: "1"
agents:
root:
instruction: Always answer by talking like a pirate
model: openai/gpt-4o
EOF
) "Hello, World"
```
A hackable multi-agent framework: with a few lines of YAML you can spin up a pool of AI agents that collaborate and use tools.
👉 github.com/docker/cagent
A hackable multi-agent framework: with a few lines of YAML you can spin up a pool of AI agents that collaborate and use tools.
👉 github.com/docker/cagent
👉https://github.com/docker/cagent
A few lines of YAML gets you a powerful team of
AI Agents!
I spent the last weeks on it, with @rumpl, @jeanlaurent and an awesome team.
🍒🍰It works great with our MCP Gateway!
👉https://github.com/docker/cagent
A few lines of YAML gets you a powerful team of
AI Agents!
I spent the last weeks on it, with @rumpl, @jeanlaurent and an awesome team.
🍒🍰It works great with our MCP Gateway!
At #MSBuild, Jim Clark will show how #Docker makes building AI apps easy with:
⚡️ Model Runner (fast, local, GPU-powered)
🔍 MCP Catalog (find tools fast)
🔐 MCP Toolkit (handles config + auth)
🗓️ 5/19 | 🕚 11:55AM: t.co/85UT3LtfGn
At #MSBuild, Jim Clark will show how #Docker makes building AI apps easy with:
⚡️ Model Runner (fast, local, GPU-powered)
🔍 MCP Catalog (find tools fast)
🔐 MCP Toolkit (handles config + auth)
🗓️ 5/19 | 🕚 11:55AM: t.co/85UT3LtfGn
Enter: Docker MCP Catalog + Toolkit
Launching this May. Built into Docker Hub.
www.docker.com/blog/introdu...
Enter: Docker MCP Catalog + Toolkit
Launching this May. Built into Docker Hub.
www.docker.com/blog/introdu...