Log inSign up
Image
user avatar
Composio
@composio
Your agent is smart. Its tools should be too. Check composio.dev
build on top of us ➡️
docs.composio.dev
Joined October 2023
42
Following
20.8K
Followers
AffiliatesRepliesArticlesMedia
  • Pinned
    user avatar
    Composio
    @composio
    Aug 6
    We ran DeepSeek V4 Flash through 4 agent harnesses (Claude Code, Codex, OpenCode, Oh My Pi) on 30 agentic tasks. A different harness won on each metric: success rate, cost, and speed. 🧵🧵🧵
    Image
  • user avatar
    Composio
    @composio
    Aug 3
    We tested DeepSeek V4 Flash against Kimi K3 and GLM 5.2 on 30 challenging agentic tasks. DeepSeek was 2.5x faster than GLM and 1.4x faster than Kimi at a similar success rate, despite using the most tokens per task. 🧵🧵🧵
    Image
  • user avatar
    Composio
    @composio
    Jul 31
    We ran Kimi K3 through 3 more agent harnesses (Pi Agent, OpenCode, and Codex) bringing the comparison to 6 harnesses across 26 agentic tasks. 2 things stood out: Codex ranked last on success despite mid-pack speed and cost, while Claude Code cost about 4x more than Hermes. 🧵🧵
    Image
  • user avatar
    Composio
    @composio
    Jul 30
    People should be free to choose the models that work best for them. Composio gives agents (open-weight or proprietary) access to the tools they need to get things done. We're proud to sign the open weights letter and join 235 organizations supporting greater choice in AI. More
    Image
  • user avatar
    Composio
    @composio
    Jul 29
    We ran Kimi K3 through 3 agent harnesses (Claude Code, Hermes, Kimi Code) on 28 identical tasks. All 3 harnesses completed the tasks at similar success rates, but the interesting story is token efficiency: the same task cost up to 30x more tokens depending on the harness. 🧵🧵