[![AI Newsletter](https://substackcdn.com/image/fetch/$s_!m7md!,w_40,h_40,c_fill,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F41327c80-fe59-416d-aa6f-ab6874177ac7_517x517.png)](https://nlp.elvissaravia.com/)
# [AI Newsletter](https://nlp.elvissaravia.com/)
SubscribeSign in
# 🤖 AI Agents Weekly: NVIDIA AVO, TrueForge, Chroma Foundation, Fragile Self-Improvement, Ornith-1.5, dots3-note, DeepSeek Vision, and More
### NVIDIA AVO, TrueForge, Chroma Foundation, Fragile Self-Improvement, Ornith-1.5, dots3-note, DeepSeek Vision, and More
Aug 22, 2026
∙ Paid
17
3
Share
In today’s issue:
  * NVIDIA AVO hits 100% on ARC-AGI-3
  * TrueFoundry open-sources TrueForge harness
  * Chroma ships Foundation agent memory
  * Self-improvement gains vanish when reshuffled
  * Ornith-1.5 self-improves to Opus level
  * dots3-note runs for days
  * DeepSeek adds vision to V4-Flash
  * Stripe acquires OpenRouter
  * Cursor rebuilds Git storage as a database
  * Harvey post-trains Tenet on Kimi K3
  * Slack Code makes coding multiplayer
  * LEGO-RL trains agents in Claude Code


And all the top AI dev news, papers, and tools.
* * *
* * *
## Top Stories
### NVIDIA AVO Solves ARC-AGI-3
[![NVIDIA AVO architecture](https://substackcdn.com/image/fetch/$s_!IPvI!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F016f1964-d0a2-4187-92aa-80b5bb6fb228_1999x1126.webp)](https://substackcdn.com/image/fetch/$s_!IPvI!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F016f1964-d0a2-4187-92aa-80b5bb6fb228_1999x1126.webp)
NVIDIA’s general-purpose coding agent AVO scored a perfect 100.00 RHAE on the ARC-AGI-3 public set, clearing all 183 levels across all 25 environments with no instructions, rules, or stated goals.
  * **The harness carries the result:** Claude Opus 5 alone scores roughly 30% on the same benchmark. Wrapping it in AVO takes it to 100%, which NVIDIA frames as evidence that system design, not model capability alone, unlocks frontier long-horizon performance.
  * **Agentic variation loop:** AVO cycles through inspect context, plan the next change, implement, evaluate with a scoring function, then diagnose and repair from failed attempts, committing accepted candidates into a growing solution lineage.
  * **Persistent memory and a supervisor:** Prior implementations, evaluation results, compiler output, and reasoning are retained so the agent resumes from current state, while a separate monitor watches for stagnation and conditionally redirects the main agent.
  * **Transfer across domains:** The same architecture was originally built for CUDA GPU kernel optimization and moved to interactive reasoning unchanged, using about 12% fewer environment actions than the prior VISTA baseline.


**[Blog](https://developer.nvidia.com/blog/nvidia-avo-reaches-100-on-arc-agi-3-demonstrating-a-frontier-level-general-purpose-architecture-for-long-horizon-autonomous-agents/)** | **[Agent Security](https://developer.nvidia.com/blog/where-security-fits-in-an-ai-agent-stack)**
* * *
### TrueFoundry Open-Sources TrueForge
[![TrueForge agent harness](https://substackcdn.com/image/fetch/$s_!6pc2!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Febce6557-11f2-408b-aaaa-fd5161b040a5_1536x1024.png)](https://substackcdn.com/image/fetch/$s_!6pc2!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Febce6557-11f2-408b-aaaa-fd5161b040a5_1536x1024.png)
TrueFoundry open-sourced TrueForge under an MIT license, a vendor-neutral agent harness that acts as the runtime layer turning an LLM into a working agent.
  * **Batteries included:** MCP tools, a skills registry, sandboxed execution, human-in-the-loop approval gates for sensitive actions, subagents, durable state for long-running tasks, and step-level tracing all ship in the box.
  * **Vendor-neutral by design:** It runs on your own infrastructure against any commercial or open-source model, with per-task switching, and the TrueFoundry AI Gateway is optional rather than required.
  * **Cost is the pitch:** On DevRev’s Enterprise-Bench, evaluated blind, TrueFoundry reports roughly 30% lower cost on identical tasks with the same model, and up to 75% savings when routing to open-source models with accuracy matched.
  * **Traction:** The repo has cleared 2,800 stars since the August 19 launch. Star it if you want to follow the project.


**[GitHub](https://github.com/truefoundry/trueforge)** | **[Docs](https://trueforge.dev)** | **[Product](https://www.truefoundry.com/trueforge)**
## This post is for paid subscribers
[Subscribe](https://nlp.elvissaravia.com/subscribe?simple=true&next=https%3A%2F%2Fnlp.elvissaravia.com%2Fp%2Fai-agents-weekly-nvidia-avo-trueforge&utm_source=paywall&utm_medium=web&utm_content=212295327)
[Already a paid subscriber? **Sign in**](https://substack.com/sign-in?redirect=%2Fp%2Fai-agents-weekly-nvidia-avo-trueforge&for_pub=nlpnews&change_user=false)
© 2026 elvis · [Privacy](https://substack.com/privacy) ∙ [Terms](https://substack.com/tos) ∙ [Collection notice](https://substack.com/ccpa#personal-data-collected)
[ Start your Substack](https://substack.com/signup?utm_source=substack&utm_medium=web&utm_content=footer)[Get the app](https://substack.com/app/app-store-redirect?utm_campaign=app-marketing&utm_content=web-footer-button)
[Substack](https://substack.com) is the home for great culture