cyfyifanchen
Joined 11 years ago
Karma
17
Submissions
8
Member since
Oct 2
Recent submissions
Comment · 1 month ago
Comment · 2 years ago
Gotta love that.
Comment · 2 years ago
Sure it will.
Comment · 2 years ago
TEN is good at real-time, multimodal, multi programming languages and cloud-edge. I doubt they are.
Comment · 2 years ago
Experience voice, vision and RAG at https://agent.theTen.ai
Comment · 2 years ago
Hi, greetings from TEN! We hope to make you feel better on this Monday blues.
The TEN Framework is an open-source framework that enables developers to quickly build real-time multimodal agents (voice, video, data stream, image and text), making it easy for developers to experiment, integrate large language models, and create reusable extensions. Please feel free to try our online demo via https://agent.theten.ai/
Here is our Github: https://github.com/TEN-framework/TEN-Agent (If you like this open source project, please help us by clicking the GitHub star ）
Here is our blog: https://ten-framework.medium.com/ (Design, engineering, and everything else about TEN)
Here is our documentation wiki: https://doc.theten.ai/
Want to run TEN Agent locally in under 5 minutes? Follow this guide: https://doc.theten.ai/ten-agent/getting_started…
If you want to be a TEN contributor, here is the guide you need:TEN-Agent/docs/code-of-conduct/contributing.md at main · TEN-framework/TEN-Agent
And as we are open-source, we would greatly appreciate any feedback that you may be willing to share with us. If there is anything that we can help with making TEN more available to others, please let us know!
Hope you enjoy using TEN. Have a nice time
Raven brings Claude Code, Codex, and its own Research, Code, Design, and Oncall agents into a shared task graph. The idea is to let different agents handle the parts of a project they are suited to, with shared memory across subagents and context carried across sessions.
The RSI work extends to the harness itself: prompts, policies, strategy code, and playbooks. Raven's specialist harnesses and orchestration layer can be improved independently. Candidate changes are evaluated before adoption. This concerns Raven's own components; it doesn't rewrite Claude Code or Codex internals.
We've used Raven for long-running research and experimentation workflows and for building a Godot game. The repository includes examples and outputs, along with installation instructions. We're also exploring how to develop and refine specialist agents for particular domains.
Raven is pre-alpha and Apache-2.0 licensed. The self-improvement work is experimental; the Curator currently ships in the repository rather than the installed package.
Code and examples: https://github.com/EverMind-AI/Raven
Where do you find coordination between agents breaks down today? We'd also be interested in what evidence you'd want before trusting an agent-generated change to its own harness.