OpenSquilla
PulseAugur coverage of OpenSquilla — every cluster mentioning OpenSquilla across labs, papers, and developer communities, ranked by signal.
- 2026-07-25 product_launch OpenSquilla has released a new open-source agent framework featuring dynamic LLM routing. source
- 2026-07-06 product_launch OpenSquilla released version 0.5.0 Preview 1, featuring multi-model integration for AI agents. source
- 2026-07-06 product_launch OpenSquilla released version 0.5.0 Preview 1, featuring multi-model integration and collaboration capabilities. source
- 2026-07-01 product_launch OpenSquilla released version 0.4.0 of its AI coding agent, introducing a self-verification mechanism for code. source
- 2026-06-30 product_launch OpenSquilla, an open-source AI Agent project, released version 0.4.0, introducing a coding workflow with a self-verification mechanism. source
- 2026-06-03 product_launch OpenSquilla has launched a new feature called Meta Skill, enabling the chaining of multiple skills for complex automated workflows and introducing intelligent model routing for cost optimization. source
-
OpenSquilla releases dynamic LLM routing agent framework
OpenSquilla has released a new open-source agent framework that uses a local classifier called SquillaRouter to dynamically route user requests to the most cost-effective LLM capable of handling the task. This approach …
-
AI-native smartphone STEPX Neo wins "Gem of the Exhibition" award at 2026 WAIC
The STEPX Neo, a smartphone designed with large model-native intelligence, has been awarded the "Gem of the Exhibition" at the 2026 WAIC. This device features the world's first intelligent agent-native operating system,…
-
OpenSquilla integration beats GPT-5.6-sol on DRACO benchmark for cost and quality
A new evaluation of the DRACO benchmark's Brave Search group shows that GPT-5.6-sol has entered the rankings with an average score of 63.99 and a cost of $1.71 per task. However, an integrated solution called OpenSquill…
-
New agentic routing paradigm uses data flywheel for specialized LLMs
Researchers have introduced Harness-Native agentic routing, a new paradigm for managing large language model agents. This approach addresses the increasing specialization of AI models by enabling an execution harness to…
-
OpenSquilla integrates multiple Chinese AI models to top benchmarks, outperforming Fable 5 and GPT-5.5 on cost
OpenSquilla has released version 0.5.0 Preview 1 of its AI Agent project, introducing a multi-model integration and collaboration feature. This new approach organizes multiple Chinese AI models, including DeepSeek v4, G…
-
OpenSquilla AI coding agent adds self-verification for code correctness
OpenSquilla has released version 0.4.0 of its AI coding agent, introducing a "self-verification" mechanism that allows AI to test its own code before submission. This feature aims to address the trust deficit in AI-gene…
-
招商银行成立新租赁公司，AI项目OpenSquilla发布新版本
招商银行的全资子公司招银金融租赁有限公司在天津成立了一家名为天津丰泰设备租赁有限公司的新公司。该公司注册资本为10万人民币，经营范围包括金融租赁公司在境内保税地区设立项目公司开展融资租赁业务。此外，开源AI Agent项目OpenSquilla发布了0.4.0版本，引入了编码工作流的“自我验证”机制。
-
Open Source Agent Minimizes LLM Token Consumption
OpenSquilla is an open-source agent designed to minimize token consumption when performing tasks with large language models. This approach addresses the significant cost associated with token usage in LLM economics. The…
-
OpenSquilla releases MetaSkill framework; NSA uses Anthropic's Mythos model
OpenSquilla has released the MetaSkill framework, which aims to give AI agents more control over their own processes for automating complex tasks. Meanwhile, the NSA is reportedly using Anthropic's advanced Mythos model…
-
OpenSquilla launches Meta Skill for complex AI workflows and cost savings
OpenSquilla has released a new feature called Meta Skill, which allows for the chaining of multiple individual skills into a single, end-to-end workflow. This enables more complex, automated tasks that previously requir…
-
OpenSquilla platform slashes AI token costs with brain-inspired memory
OpenSquilla, a new open-source platform, aims to significantly reduce AI token costs by up to 80%. It utilizes a novel memory architecture inspired by the human brain and intelligent query routing. This approach is desi…