In 30 seconds
In an NVIDIA partner promotion, Matthew Berman recommends running agents locally and describes AnythingLLM's collaboration with NVIDIA. He highlights local models and a community hub for sharing agent workflows, including drafting emails.
- 1Local agentsBerman recommends running agents locally when giving them access to personal information.
- 2Local models on RTX PCsHe describes an NVIDIA and AnythingLLM collaboration focused on locally powered models and RTX AI PCs.
- 3Community workflowsThe AnythingLLM community hub lets users share and discover agent behaviors, including draft email workflows.
Takeaways
- Berman recommends local agents as a way to keep personal information on a local system.
- He says AnythingLLM and NVIDIA are sharing how to run agents with local models on RTX AI PCs.
- AnythingLLM's community hub lets people share and find agent workflows, including email drafting.
Read the edited text by chapter
Local agents and community workflows
Berman recommends local agents and discusses an AnythingLLM collaboration with NVIDIA. He describes a hub for sharing workflows such as creating email drafts.
I strongly recommend running your agents locally. It lets you give them access to personal information while feeling more secure about it. NVIDIA is partnering with AnythingLLM to show how to build agents locally and run them with local models.
AnythingLLM is built on llama.cpp to work faster and better on NVIDIA RTX AI PCs. I think AnythingLLM is making a major push into agents.
The community hub lets people build and share agent behaviors and discover workflows created by others, including agents that generate and open drafts for Gmail or Outlook.
Those workflows can run at speed on NVIDIA RTX PCs. Check out AnythingLLM and NVIDIA’s information about how GeForce RTX GPUs power AI; thanks to NVIDIA for supporting the segment.
More from this channel
14:45EN
Matthew Berman· Oct 29, 2026Matthew Berman Examines Google’s Gemini 4 Carbon AnnouncementMatthew Berman · Forward FutureMatthew Berman reviews Google’s reported benchmark results, staged rollout and pricing for Gemini 4 Carbon, while noting he has not yet used the model.
21:11ENMatthew Berman· Oct 28, 2026Matthew Berman tests DeepSeek V4.1 Flash: coding, vision and local appsMatthew Berman · Forward FutureA hands-on tour of visual coding, image reasoning, local applications and provider economics reveals both impressive results and visible flaws.
34:21ENMatthew Berman· Oct 27, 2026Matthew Berman Examines Anthropic’s IPO Filing, AI Growth and GovernanceMatthew Berman, Sam Altman · Forward FutureThe presenter reviews the S-1’s financial metrics, compute strategy and voting structure while questioning the tension between rapid AI development and safety.
0:26ENMatthew Berman· Oct 25, 2026Sam Altman on Human Values and Problem-Solving in an AI WorldSam Altman · OpenAIIn a short interview excerpt, Altman considers the enjoyment of solving hard problems and the human role in interpreting results.
0:36ENMatthew Berman· Oct 25, 2026Kimi K3.1 and a Rubik’s Cube Solver DemonstrationMatthew Berman · Forward FutureMatthew Berman shows a scrambled virtual cube being solved and gives the Kimi K3.1 test a favorable assessment.
0:21ENMatthew Berman· Oct 24, 2026An AI-Generated Kimi Benchmark Chart Used Invented ScoresMatthew Berman · Forward FutureMatthew Berman asks for a graph of Kimi K3.1 Pro benchmarks, then discovers that the displayed figures are illustrative placeholders.