AI & ML interests

None defined yet.

Recent Activity

aittalamย  updated a model 20 days ago
mozilla-ai/llamafile_0.10.0_alpha
aittalamย  published a model 21 days ago
mozilla-ai/llamafile_0.10.0_alpha
daavooย  updated a Space about 1 month ago
mozilla-ai/README
View all activity

Articles

daavooย 
posted an update 20 days ago
view post
Post
1845
2025: The Year of Agents.
2026: The Year of Local Agents?

Relying on cloud-hosted LLMs is often overkill. While frontier models still lead in complex coding, local models are now more than capable of handling many agentic workflowsโ€”with zero latency and total privacy.

To help bridge the gap between local inference and usable agents, Iโ€™m releasing agent.cpp: https://github.com/mozilla-ai/agent.cpp

It provides minimal, high-performance building blocks for agents in C++, built directly around the awesome llama.cpp ecosystem.
Stop sending your data to a remote API. Start building and running agents on your own hardware.
  • 1 reply
ยท
daavooย 
updated a Space about 1 month ago
daavooย 
posted an update 5 months ago
view post
Post
177
A new minor version of any-agent (1.1.0 ) is out ๐Ÿš€

https://github.com/mozilla-ai/any-agent/releases/tag/1.1.0

- ๐ŸคImprovements for Small Language Models
We recommend tinyagent to be used as default when working with Small Language Models.
- ๐Ÿงช Extending and Improving test suite.
For example, we now include a cookbook and an integration test running a Small Language Model (Qwen 1.7B)
- ๐Ÿ“–Extending and Improving docs
stefan-frenchย 
posted an update 6 months ago
view post
Post
227
๐Ÿš€ We recently released any-llm: https://github.com/mozilla-ai/any-llm

๐Ÿง‘โ€๐Ÿ’ป It's easy to get started:

from any_llm import completion
import os

# Make sure you have the appropriate environment variable set
assert os.environ.get('MISTRAL_API_KEY')
# Basic completion
response = completion(
    model="mistral/mistral-small-latest", # <provider_id>/<model_id>
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

๐Ÿ“– Read more about it here: https://huggingface.co/blog/mozilla-ai/introducing-any-llm
stefan-frenchย 
posted an update 6 months ago
view post
Post
2199
๐Ÿš€ We just released the WASM Agent Blueprint!

It shows how to run Python-based AI agents directly in your browser using WebAssembly (WASM) via Pyodide and the OpenAI Agents SDK. There are no installs, it runs straight in your browser.

Try it out and explore the code ๐Ÿ‘‰ https://github.com/mozilla-ai/wasm-agents-blueprint
  • 1 reply
ยท
daavooย 
posted an update 8 months ago
stefan-frenchย 
posted an update 8 months ago
daavooย 
posted an update 8 months ago
view post
Post
1532
Have you heard about the Agent2Agent Protocol (A2A)?

We have just released an option in https://github.com/mozilla-ai/any-agent to serve with A2A any of the supported agent frameworks (Agno, Google ADK, Langchain, LlamaIndex, OpenAI Agents SDK, smolagents and tinyagent)!

Check the docs https://mozilla-ai.github.io/any-agent/serving/

# google_expert.py
from any_agent import AgentConfig, AnyAgent
from any_agent.config import ServingConfig
from any_agent.tools import search_web

agent = AnyAgent.create(
    "google",
    AgentConfig(
        name="google_expert",
        model_id="gpt-4.1-nano",
        instructions="You must use the available tools to find an answer",
        description="An agent that can answer questions about the Google Agents Development Kit (ADK).",
        tools=[search_web]
    )
)

agent.serve(ServingConfig(port=5001))
daavooย 
posted an update 8 months ago
view post
Post
1372
We've just released a new version of https://github.com/mozilla-ai/any-agent , including a Python implementation of https://huggingface.co/blog/tiny-agents!

Give it a โญ!

from any_agent import AnyAgent, AgentConfig
from any_agent.config import MCPStdioParams

agent = AnyAgent.create(
    "tinyagent",
    AgentConfig(
        model_id="gpt-4.1-nano",
        instructions="You must use the available tools to find an answer",
        tools=[
            MCPStdioParams(
                command="uvx",
                args=["duckduckgo-mcp-server"]
            )
        ]
    )
)

result = agent.run(
    "Which Agent Framework is the best??"
)
print(result.final_output)

daavooย 
posted an update 9 months ago
view post
Post
1947
We have just released a new version ofโญhttps://github.com/mozilla-ai/any-agent โญexposing an API to be used in async contexts:

import asyncio
from any_agent import AgentConfig, AnyAgent, TracingConfig
from any_agent.tools import search_web

async def main():
    agent = await AnyAgent.create_async(
        "openai",
        AgentConfig(
            model_id="gpt-4.1-mini",
            instructions="You are the main agent. Use the other available agents to find an answer",
        ),
        managed_agents=[
            AgentConfig(
                name="search_web_agent",
                description="An agent that can search the web",
                model_id="gpt-4.1-nano",
                tools=[search_web]
            )
        ],
        tracing=TracingConfig()
    )

    await agent.run_async("Which Agent Framework is the best??")

if __name__ == "__main__":
    asyncio.run(main())
daavooย 
posted an update 9 months ago
view post
Post
2064
Another day, another release in
โญhttps://github.com/mozilla-ai/any-agent โญ

You can now use MCP (Model Context Protocol) tools via SSE (Server-Sent Events):

from any_agent import AgentConfig, AnyAgent
from any_agent.config import MCPSseParams

agent = AnyAgent.create(
    "smolagents",
    AgentConfig(
        model_id="gpt-4o-mini",
        tools=[
            MCPSseParams(
                url="http://localhost:8000/sse"
            ),
        ]
    )
)
agent.run("What do MCP and SSE mean?")


See SuperGateway for an easy way to turn a Stdio server into an SSE server.
daavooย 
posted an update 9 months ago
view post
Post
1309
New release in https://github.com/mozilla-ai/any-agent ๐Ÿค–

You can now use "managed_agents" also in langchain and llama_index, in addition to the other frameworks:

from any_agent import AgentConfig, AgentFramework, AnyAgent
from any_agent.tracing import setup_tracing

framework = AgentFramework("langchain")  # also in AgentFramework("llama_index") and the rest of frameworks
setup_tracing(framework)

agent = AnyAgent.create(
    framework,
    AgentConfig(
        model_id="gpt-4.1-mini",
        instructions="You are the main agent. Use the other available agents to find an answer",
    ),
    managed_agents=[
        AgentConfig(
            name="search_web_agent",
            description="An agent that can search the web",
            model_id="gpt-4.1-nano",
            tools=["any_agent.tools.search_web"]
        ),
        AgentConfig(
            name="visit_webpage_agent",
            description="An agent that can visit webpages",
            model_id="gpt-4.1-nano",
            tools=["any_agent.tools.visit_webpage"]
        )
    ]
)
agent.run("Which Agent Framework is the best??")
  • 2 replies
ยท
stefan-frenchย 
posted an update 9 months ago
daavooย 
posted an update 9 months ago
view post
Post
2966
Wondering how the new Google Agent Development Toolkit (ADK) compares against other frameworks? ๐Ÿค”You can try it in any-agent ๐Ÿš€

https://github.com/mozilla-ai/any-agent

agent = AnyAgent.create(
    AgentFramework("google"),
    AgentConfig(
        model_id="gpt-4o-mini"
    )
)
agent.run("Which Agent Framework is the best??")

  • 1 reply
ยท
daavooย 
posted an update 9 months ago
view post
Post
1842
After working on agent evaluation๐Ÿ”๐Ÿค– the last weeks, we started to accumulate code to make trying different agent frameworks easier. From that code, we have built and just released a small library called any-agent.


Give it a try and a โญ: https://github.com/mozilla-ai/any-agent

from any_agent import AgentConfig, AgentFramework, AnyAgent

agent = AnyAgent.create(
    AgentFramework("smolagents"),  # or openai, langchain, llama_index
    AgentConfig(
        model_id="gpt-4o-mini"
    )
)
agent.run("Which Agent Framework is the best??")