• Trends
  • Topics
  • Nodes
Search for keywords, #hashtags, $sites, add a dash to exclude, e.g. -$theonion.com

From composio.dev

Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

0 0

This blog-post compares the coding capabilites of new Gemini 2.5 Pro experimental and Claude 3.7 Sonnet (thinking)

on Mar 31

From composio.dev

Gemma 3 27b vs. QwQ 32b vs. Mistral 24b vs. Deepseek r1

0 0

In this blog post, we did a comprehensive comparison of Qwen QwQ 32b, Gemma 27b, Mistral small 3.1 24b, and Deepseek r1.

on Mar 23

From composio.dev

Discover The Best Agentic AI Developer Tools

0 1

Explore powerful Developer focused Agentic AI Tools that think, code, and create alongside developers. From smart coding assistants to autonomous dev agents, discover tools that transform how we build the future.

on Feb 15

From composio.dev

Notes on the new Deepseek r1

0 0

In this blog post we explore the newly released Deepseek r1, technical details, remarks from people on it, and comparison with o1 and o1 pro.

on Jan 24

From composio.dev

Notes on the new Deepseek v3

0 0

In this blog we go thorough the new Deepseek v3 and compare it with GPT-4o and 3.5 Sonnet across reasoning, math, coding, & writing tasks.

on Jan 2

From composio.dev

Gemini 2.0 vs Flash vs OpenAI o1 and Claude 3.5 Sonnet

0 0

Google has finally woken up and decided to drop the bombshell Gemini 2.0, completing the AI trifecta. Google has launched two new

on Dec 27

From composio.dev

OpenAI o1 vs Claude 3.5 Sonnet: Which One’s Really Worth Your $20?

0 0

This article explores key observations about OpenAI o1, comparing its math, coding, and writing abilities to Claude 3.5 Sonnet.

on Dec 13

From composio.dev

AgentAuth: Seamless Authentication for AI Agents with 250+ Tools

0 0

Star 11.5k+ composio AgentAuth Auth for AI Agents to Act on Users Behalf Apps Docs Trusted by Engineers From Authentication Designed for

on Nov 26

From composio.dev

Tool design is all you need for SOTA SWE agents

0 0

This is the technical report highlighting SWE-Kit, a toolkit and an IDE for AI agents. We demonstrated how our agent became SOTA on SWE bench.

on Nov 6

From composio.dev

Notes on Anthropic's Computer Use Ability

0 0

This article takes a deep dive into Claude Computer Use. How it works, the use cases, and what the future holds for AI agents.

on Oct 25

From composio.dev

OpenAI o1-preview: A Detailed Analysis

0 0

This article provides an in-depth vibe-check of the o1-preview model’s capabilities across tasks like coding, math, and reasoning.

on Sep 23

From composio.dev

Improving GPT 4 Function Calling Accuracy

0 1

Join our Discord Community and check out what we're building! Introduction to GPT Function Calling Large language models have recently been given the ability to perform function calling. Given the details(function-schema) of a number of functions, the LLM will be able to select and run the...

on May 9