Martin Krasser
@krasserm.bsky.social
Freelance ML and AI engineer, distributed systems developer, https://martin-krasser.com
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 👇
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 👇
August 7, 2025 at 4:38 PM
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 👇
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 👇
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...
Hybrid Groups
YouTube video by Gradion AI
www.youtube.com
July 25, 2025 at 6:54 AM
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...
Reposted by Martin Krasser
Multi-user, multi-agent platform: github.com/gradion-ai/h...
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
github.com
June 20, 2025 at 6:21 AM
Multi-user, multi-agent platform: github.com/gradion-ai/h...
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".
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.
February 6, 2025 at 5:40 PM
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".
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.
February 4, 2025 at 5:34 AM
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.
I just released freeact - a lightweight Python implementation of AI agents that use code actions to dynamically interact with and adapt to their environment.
December 30, 2024 at 11:12 AM
I just released freeact - a lightweight Python implementation of AI agents that use code actions to dynamically interact with and adapt to their environment.