Martin Krasser's Avatar

Martin Krasser

@krasserm.bsky.social

Freelance ML and AI engineer, distributed systems developer, https://martin-krasser.com

13 Followers  |  3 Following  |  11 Posts  |  Joined: 19.11.2024  |  1.4996

Latest posts by krasserm.bsky.social on Bluesky

https://gradion-ai.github.io/agents-nanny/2025/08/06/agent-authorization-without-the-pain/

The key is a clean separation of concerns: your agents focus on reasoning and tool use 🧠, while a service like Composio
handles API integration, authorization, and MCP server hosting for you 🔧

blog post: t.co/qPpGVROEgD

07.08.2025 16:40 — 👍 1    🔁 1    💬 0    📌 0
Post image

Agent authorization and API integrations can be a challenge 🤔.

Our latest blog post explores how you can authorize your agents to access 250+ APIs (Gmail, Slack, Notion, ...) with just a few lines of code, letting you focus on core logic, not plumbing and OAuth details 👇

07.08.2025 16:38 — 👍 1    🔁 1    💬 1    📌 0

Agents have the full context of a conversation and act on behalf of users. Build your own agents in minutes with Hybrid Group's agent builder. Find out more at github.com/gradion-ai/h...

25.07.2025 06:55 — 👍 1    🔁 1    💬 0    📌 0
Hybrid Groups
YouTube video by Gradion AI Hybrid Groups

Hybrid Groups is agentic AI for human teams. Agents understand and contribute to conversations on Slack and GitHub. Watch the demo 🎥 www.youtube.com/watch?v=OxOm...

25.07.2025 06:54 — 👍 2    🔁 3    💬 1    📌 0
Preview
GitHub - gradion-ai/hybrid-groups: A multi-user, multi-agent group collaboration platform and library A multi-user, multi-agent group collaboration platform and library - gradion-ai/hybrid-groups

Multi-user, multi-agent platform: github.com/gradion-ai/h...

20.06.2025 06:21 — 👍 1    🔁 1    💬 0    📌 0
Exploring DeepSeek-R1's agentic capabilities through code actions - Martin Krasser's Blog

Blog post: krasserm.github.io/2025/02/05/d...
Repository: github.com/gradion-ai/f...

06.02.2025 17:40 — 👍 0    🔁 0    💬 0    📌 0

New blog post: Exploring DeepSeek-R1's agentic capabilities through code actions (link below). DeepSeek-R1 doesn't support tool use natively, but can be used for agentic tasks through code actions. The post also covers limitations like long reasoning traces and "underthinking".

06.02.2025 17:40 — 👍 0    🔁 0    💬 1    📌 0

Additional RL on agentic tool use via code actions should further improve performance. Find evaluation details at github.com/gradion-ai/f....

04.02.2025 05:35 — 👍 0    🔁 0    💬 0    📌 0
Post image

DeepSeek R1 surpasses Claude 3.5 Sonnet on agentic tasks even if it wasn't trained for it. In our experiments, we leveraged DeepSeek-R1's strong coding abilities to act via code and initial results look promising.

04.02.2025 05:34 — 👍 0    🔁 0    💬 1    📌 1

Learn how freeact agents work:
Docs: gradion-ai.github.io/freeact/
Repo: github.com/gradion-ai/f...

30.12.2024 11:13 — 👍 0    🔁 0    💬 0    📌 0

Freeact agents write their actions in code, rather than just being agents for writing code. This design provides a vast action, space—no JSON tool configs required.

30.12.2024 11:13 — 👍 0    🔁 0    💬 1    📌 0
High-level architecture of a freeact agent system

High-level architecture of a freeact agent system

I just released freeact - a lightweight Python implementation of AI agents that use code actions to dynamically interact with and adapt to their environment.

30.12.2024 11:12 — 👍 1    🔁 0    💬 1    📌 0

@krasserm is following 1 prominent accounts