Before: My love life runs on Agent Zero defaults now: stopped after 2 consecutive unusable responses. After: stopped after 5 consecutive unusable responses 🙃

try , download https://openai.com/codex/

In the **AGENTIC ERA**, and already entering the **LOOPy ERA**, Vercel is launching a framework for creating agents from a folder-based structure. ## What Is Vercel EVE? **Vercel EVE** is an open-source framework for building and deploying AI agents using an architecture based on files and folders. In practice, the entire agent is organized inside a single folder: ```text agent/ ├── agent.ts ├── instructions.md ├── skills/ ├── tools/ ├── subagents/ ├── connections/ ├── channels/ ├── schedules/ ├── sandbox/ └── evals/ ``` Each directory represents one of the agent’s capabilities: * `agent.ts`: defines the model and the main configuration; * `instructions.md`: contains the system prompt and global rules; * `skills/`: specialized procedures and knowledge; * `tools/`: functions the agent can execute; * `subagents/`: specialized agents for more complex tasks; * `connections/`: APIs, databases, and MCP servers; * `channels/`: Slack, Discord, an API, or a custom interface; * `schedules/`: automated and scheduled tasks; * `sandbox/`: isolated code execution; * `evals/`: behavior and security tests. EVE’s main differentiator is automatic component discovery. You do not need to manually import every skill, tool, or subagent into the main file. The framework scans the folder structure, identifies the components, and generates a manifest with everything connected. This turns the file system into a kind of declarative configuration for the agent. Instead of writing one massive central file: ```ts import toolA from "./tools/toolA"; import toolB from "./tools/toolB"; import skillA from "./skills/skillA"; import investigator from "./subagents/investigator"; ``` You simply place each component in the correct folder, and EVE handles the integration during compilation. In addition to organization, EVE adds capabilities required for production: * durable sessions; * recovery after failures or redeployments; * sandboxed code execution; * human approval for risky actions; * testing before deployment;

I love running Qwen on my VPSs. I’m currently using version 3.6 and now testing 3.8. We’re living through an incredible moment—learning the foundations of what makes us special. Qwen @Alibaba_Qwen Qwen3.8 is launching and going open-weight soon! With a massive 2.4T parameters, this model is continuously evolving. We believe it’s one of the most powerful model available today, compatible to leading frontier AI models , second only to Fable 5. You don't have to wait to test it. Just now, the Qwen3.8-Max-Preview made its debut on Alibaba’s Token Plan, Qoder, and QoderWork. Be among the very first to try it out. Can't wait to hear what you build. Stay tuned! Token Plan international：https://qwencloud.com/pricing/token-plan

A lot of people are creating prompts and setups to simulate Fable, so I gathered the best ideas and turned them into a Skill. Take a look and see whether it is useful for you. If it is not, please tell me why. I want to understand what is missing so I can improve it. Fable Mode makes the model work with a more disciplined methodology on complex tasks. It enforces a five-stage workflow: 1. Scope — understand the objective, expected deliverable, constraints, and what could go wrong. 2. Evidence — verify facts, files, sources, and assumptions before reaching conclusions. 3. Attack — challenge the plan itself, looking for weaknesses, risks, and overlooked issues. 4. Verification — test and validate the result before declaring it complete. 5. Reporting — explain what was done, what was validated, and what limitations remain. It also guides the model to: - use stronger models for planning and review; - use lower-cost models for straightforward execution; - choose the appropriate reasoning effort level; - avoid unnecessary clarification questions; - never rely solely on memory; - turn successful workflows into reusable methods. In one sentence: Fable Mode doesn't change the AI's intelligence—it changes how the AI plans, verifies, and delivers its work. It is especially valuable for research, strategy, software development, project analysis, and any task where mistakes can significantly impact the final outcome.