The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

Joined April 2026
Photos and videos
Multica retweeted
Heavily testing MiniMax M3 for multi-agent collaboration.
Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities - Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas - MiniMax Sparse Attention scales context to 1M - Natively Multimodal from Step Zero API: platform.minimax.io Token Plan: platform.minimax.io/subscrib… 🚀New! MiniMax Code: code.minimax.io Weights & Tech Report in ~10 Days
10
7
99
21,216
Multica retweeted
More than a month after its release, @MulticaAI has achieved a small milestone: Over 300 billion tokens are consumed on the platform every week. The goal for the next two months is to reach 1T tokens per week. github.com/multica-ai/multic…
2
3
20
6,856
Multica retweeted
In case you don't know, @MulticaAI already supports most desktop platforms. iOS is coming soon.
5
1
40
9,752
How to create an Agent team based on Kimi K2.6. x.com/MulticaAI/status/20463…

Meet Kimi K2.6: Advancing Open-Source Coding 🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2) What's new: 🔹Long-horizon coding - 4,000 tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization). 🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP Framer Motion, Three.js 3D. 🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100 files. 🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops. 🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop. - K2.6 is now live on kimi.com in chat mode and agent mode. For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code - 🔗 API: platform.moonshot.ai 🔗 Tech blog: kimi.com/blog/kimi-k2-6 🔗 Weights & code: huggingface.co/moonshotai/Ki…
1
1
11
7,848
Multica retweeted
Multica can already replace Jira for small teams. Plus, you can manage your agents in the same place. It's open source, self-hosted locally, and free. github.com/multica-ai/multic…
Apr 20
New policy from @Atlassian: Unless you opt out by August 17th 2026, data from Jira and Confluence will automatically be used for AI training. Some data cannot be opted out at all on some plans. x.com/kepano/status/16886107…
9
12
110
25,953
Multica retweeted
Apr 14
MulticaのRepositories、一見githubのURL入れないといけない雰囲気だけどローカルのファイルパスで使えるんだな ダメ元でやってみないとわからんなこれ 神
3
1
11
5,736
Multica retweeted
We created the open-source version of Routines in Claude Code. Introducing Multica Autopilot: Run your routines locally with any agent (Opencode, Codex, Hermes, Openclaw). github.com/multica-ai/multic…
Apr 14
Now in research preview: routines in Claude Code. Configure a routine once (a prompt, a repo, and your connectors), and it can run on a schedule, from an API call, or in response to an event. Routines run on our web infrastructure, so you don't have to keep your laptop open.
16
39
310
62,465
Multica retweeted
The open-source community is INSANE 🤯 Claude Code routines dropped literal hours ago, and this guy's already shipped a clone. Meet Multica Autopilot: Now you can run routines entirely locally using whatever agent you want (Opencode, Codex, Hermes, OpenClaw etc). repo in 🧵↓
Apr 14
Now in research preview: routines in Claude Code. Configure a routine once (a prompt, a repo, and your connectors), and it can run on a schedule, from an API call, or in response to an event. Routines run on our web infrastructure, so you don't have to keep your laptop open.
32
73
617
136,258
Multica 🙌
3
1
13
5,584
on my way
5
2
8
4,315