Benji Webber

often wrong, never false. Discover. Create. Celebrate. // Building reliable local AI

[Benji Webber @selfhosted4lyf]

@katiekirsch @a16z Yes let’s. What’s the best way to get in contact?

[Rohan Paul @rohanpaul_ai]

A new Stanford paper just proved that decentralized multi-agent systems can beat Claude Code and Codex on complex coding tasks, running up to 2.49× faster!

DeLM tackles a key bottleneck in multi-agent systems: time wasted repeating work and waiting on other agents.

DeLM replaces the central coordinating agent with a shared context and task queue. Agents pick up tasks independently, share discoveries as they happen, and build on each other’s progress. When one agent finds a solution or hits a dead end, the others can use that information immediately.

DeLM beats state-of-the-art in both speed and accuracy on long-horizon tasks from Terminal-Bench 4.0, DeepSWE v1.1, and ProgramBench:

- Up to 2.49× faster execution than the vanilla Claude Code and Codex baselines
- Up to +19.2 percentage points in accuracy over the vanilla Claude Code and Codex baselines
- Up to +19.9 points in ProgramBench test pass rate within the same 120-minute budget

Built on Codex and Claude Code. Code and 720 trajectories are available so you can explore how the agents collaborate! An open-source plugin lets you try DeLM directly in Codex and Claude Code.

[Benji Webber @selfhosted4lyf]

@Teknium @iAmHenryMascot Wow lots of haters out there. I took this as a positive and vision oriented.

[Benji Webber @selfhosted4lyf]

@suraj_sharma14 builder

[Benji Webber @selfhosted4lyf]

@zainmfj Well done looks solid. Is the software open source or at least an api to connect other agents to pull data?

[Benji Webber @selfhosted4lyf]

@ghostai Have you made any information public besides what’s on the order page?

[Benji Webber @selfhosted4lyf]

Basically Opus 4.8 quality with MoE speed. YES PLEASE!

[Reflection @reflection_ai]

Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active.

- Frontier reasoning efficiency
- Advances the Western open frontier on coding & agentic tasks
- Trained end-to-end from scratch

Full weights release this month.

Learn more about Beam: https://t.co/c3Qx2cpM8G

[CopilotKit🪁 @CopilotKit]

Or use the OS versions:

• OpenMuse (3.8k stars)
• OpenBot (6k stars)
• OpenDots (2.3k stars)
• OpenTag (1.2k stars)

Each template works with ANY agent harness.

Includes generative UI, automatic learning, and is self-hostable.

[Benji Webber @selfhosted4lyf]

@Ga_Vasques Great list. Would love to see your version for non-coding specific agents by type. Like I use Paseo/Hermes/OMP all for different purposes.

[Aleph Alpha @Aleph__Alpha]

Small bird, fast wings, Kolibri is here.

78B parameters. 3.46B active. Up to 1M tokens of context. Built in Europe.

Now the weights are yours. Run it on your own hardware, under Apache 2.0.

[Benji Webber @selfhosted4lyf]

One of the most innovative companies out there for real world solutions. Huge.

[Cua @trycua]

1/ We're reimagining what it means for your agents to work with all your computers.

Today we're excited to share Cua Spaces, built on Cua Driver and our virtualization stack, rolling out on macOS today.

Download it now, it's free and source-available: https://t.co/hynYqez0f7

[Victor M @victormustar]

Alert: Cloudflare just dropped a Jev alternative on Hugging Face 🚨 (Apache 2.0)

https://t.co/vEcHLoQZA9

[Atai Barkai @ataiiam]

🎉 Introducing 𝙾𝚙𝚎𝚗𝙳𝚘𝚝𝚜

Self-hostable, always-on AI coworkers that works with ANY agent harness.

Includes:
- Computer use: browser, terminal & files
- Bring agents to Slack, Teams etc
- Spaces and Pages for projects
- Voice calls
- Web and Mobile

Repo → https://t.co/j6URR886Dt

Powered by @CopilotKit and AG-UI.

Clone this template and customize it however you want. Enterprise-ready.

[Benji Webber @selfhosted4lyf]

@katiekirsch Any good events you recommend attending to talk in person regarding a16z openings for SF Tech Week?

[Benji Webber @selfhosted4lyf]

@no_stp_on_snek Exactly

[Tom Turney @no_stp_on_snek]

LocalAI folks see this coming a mile away. OpenAI won’t be the only ones.

[Benji Webber @selfhosted4lyf]

@yacineMTB Please say music please say music

[Benji Webber @selfhosted4lyf]

@0xSero Tesla v100 32gb, yes, yes

[0xSero @0xSero]

Permanent underclass is permanently cancelled.

Thanks Qwen

[Benji Webber @selfhosted4lyf]

@ashxhart Champion of the people