When working on agent workflows or autonomous agent loops, a major bottleneck affecting experience is: every small branch decision, tool routing, task completion check, or safety interception, if all handled by expensive reasoning LLMs, not only brings seconds of delay per call, but token costs also...
Summary
This article introduces the open-source list awesome-jev-projects, which decouples System 1 fast decision models from System 2 reasoning LLMs to optimize AI agent workflows, reduce latency and costs, and provide code-level references.
View Cached Full Text
Cached at: 09/24/26, 10:23 AM
English • 简体中文 • 日本語 • 한국어
🌐 Search and filter ↗ | 🤖 Install the Agent Skill | 📂 Categories | 🚀 Submit a project (Issue only)
Similar Articles
@realfxw: The biggest headache when building an Agent isn't usually the model logic, but getting it online to 'fetch data'—anti-crawling, login authentication, rate limiting; it often gets stuck at the API level. Recommend checking out the open-source project Agent-Reach, which is like equipping your AI Agent with a full-web 'data collection exoskeleton': Integrates mature ecosystems:…
Agent-Reach is an open-source project that provides one-click web data collection capabilities for AI Agents, integrating multiple tools to solve issues like anti-crawling and authentication.
@AxtonLiu: https://x.com/AxtonLiu/status/2073791557547794579
This article discusses the concept of Agent OS, emphasizing the division of tasks into multiple workstations (fetch, refine, verify, confirm) through specialization, each managed by an independent Agent to achieve controllable automation. The author uses the example of digesting browser tabs to demonstrate how specialization isolates context, responsibility, and risks, ensuring the accuracy and reliability of AI output.
@wsl8297: When running complex tasks with AI agents, the most painful thing is often not that the model isn't strong enough, but that as the conversation gets longer, the context starts to overflow. You have to keep filling in background details, re-explaining the process, plus the redundant logs from tool calls — tokens just gush out like a broken pipe. Recently, I saw TencentDB Agent Memory open-sourced by Tencent...
Tencent has open-sourced TencentDB Agent Memory, which solves the AI agent long-context overflow problem through hierarchical memory management (symbolic short-term memory + hierarchical long-term memory). Benchmarks show token consumption reduced by up to 61% and task success rate improved by over 50%.
@MinLiBuilds: Tonight’s homework is here. DeepSeek officially published a super-long technical article. It’s about Super-agent, a more autonomous Agent system. The core idea: For a single task, the bottleneck is the model. For multiple tasks, the bottleneck is the human. One person can keep tabs on at most 3 to 5 sessions at once. Any more and your brain…
DeepSeek has published an in-depth technical article introducing Super-agent, an autonomous agent system that uses a two-tier Router + Worker architecture to address bottlenecks in concurrent task execution. In testing, p95 completion time fell from 29.5 minutes to 15.7 minutes, and the prototype has been open-sourced.
@Xudong07452910: Many people's default habit when using AI coding is: go straight to the strongest model. For the same task, should Sonnet or Opus do it? Most of the time this decision is made on a whim. So this paper Agent-as-a-Router raises a very practical question: if different models excel at different tasks…
This paper proposes the Agent-as-a-Router framework, which transforms model routing into a dynamic, iterative process. Based on task type and real-time execution feedback, it selects the most suitable LLM to improve coding performance and cost efficiency.