Kimi 2.5 Thinking Available On ChatLLM And Our CLI! It's a fantastic model and is almost 10x cheaper than the closed-source models Give it a shot
SOFTWARE
-
Claude Code Gets Customizable Spinner Verbs Feature
By
–
In the next version of Claude Code, you can customize spinner verbs for yourself and your team
-
OpenAI releases Prism LaTeX workspace with GPT-5.2 for researchers
By
–
BREAKING : OpenAI is releasing Prism, a new LaTeX native workspace for researchers where GPT-5.2 can work alongside you to help draft papers, revise citatins and more. Available to Pro users. A preparation for the "Innovators" level
-
Kill conditions for agent orchestrators to stop error loops
By
–
Interesting!
One thing that I have to always do: whenever a Claude Code starts to go wrong, I kill it, because when they fill their context with error logs and wrong ideas, they tend to keep digging their hole.
A good agent orchestrator would have "kill conditions" to just -
Moltbot AI agent connects to local models via Ollama
By
–
Now you can connect Moltbot AI agent (formerly Clawdbot) to your local models via ollama. All your data stays on your device, no API calls required. The best combo
-
Manus AI Adopts Anthropic’s Skills Standard for Reusability
By
–
Manus AI now supports Skills, a common standard introduced by Anthropic, so now you can reuse them in Manus as well.
— 🚨 AI News | TestingCatalog (@testingcatalog) 27 janvier 2026
Skill is not an issue anymore 👀 https://t.co/xqM17WGdXI pic.twitter.com/lNhAe9SOYnManus AI now supports Skills, a common standard introduced by Anthropic, so now you can reuse them in Manus as well. Skill is not an issue anymore
-
Mistral AI releases Mistral Vibe 2.0 CLI with subagents and skills
By
–
Mistral AI released Mistral Vibe 2.0, an upgraded SWE agent CLI with subagents, skills support and new unified agent modes. Now available on Team and Pro plans.
— 🚨 AI News | TestingCatalog (@testingcatalog) 27 janvier 2026
Terminal Testing Time 👀 https://t.co/eD1Rwekgj3 pic.twitter.com/PeNLLj28sPMistral AI released Mistral Vibe 2.0, an upgraded SWE agent CLI with subagents, skills support and new unified agent modes. Now available on Team and Pro plans. Terminal Testing Time
-
LobeHub: multi-model, direct API, agent marketplace, 70k GitHub stars
By
–
Claude Cowork: $200/month. One model. macOS only.
Manus: VM-based browsing. Slow. Unstable. Expensive. LobeHub:
→ Multi-model support (switch freely)
→ Direct API access (faster, more accurate)
→ Agent marketplace to discover and remix
→ 70k GitHub stars foundation More -
Build a Twitter growth pipeline with multi-agent system in 10 minutes
By
–
Built a Twitter growth pipeline in 10 minutes:
→ Agent 1: monitors trends
→ Agent 2: researches sources
→ Agent 3: drafts threads
→ Agent 4: prepares posts Supervisor orchestrates. Agents work in parallel. Human approves before publish.
One instruction. Full content