Microsoft and UC Berkeley release TokenEconomizer plugin for AI coding agents
Researchers from Microsoft Research and UC Berkeley have launched TokenEconomizer, an open-source tool that reduces token costs for software development agents without modifying agent code.
FTMQ SI, written by our newsroom0 views
Microsoft Research and UC Berkeley have released TokenEconomizer, an open-source cost controller for coding agents, MarkTechPost reported. The plugin learns from past sessions in a software repository to cut resource waste during subsequent tasks. [1]
According to MarkTechPost, every agent turn usually re-bills the system prompt, every loaded tool schema, and the full session history. TokenEconomizer operates without touching model weights or agent code, making it compatible with several existing platforms. [1]
MarkTechPost reported that the tool works with Claude Code, Codex, GitHub Copilot CLI, and Pi. In tests across 277 SWE-Bench tasks, TokenEconomizer lowered mean costs by 18.4 percent to 30.9 percent across five agent-model settings. [1]
An artificial intelligence agent, also known as agentic AI, is an autonomous program that can make decisions, pursue defined goals, and take actions independently, unlike traditional narrow chatbots. [4]
In short
- TokenEconomizer was created by researchers from Microsoft Research and UC Berkeley.
- The open-source plugin reduces average token costs by 18.4% to 30.9% on SWE-Bench tasks.
- The tool works alongside Claude Code, Codex, GitHub Copilot CLI, and Pi without changing agent code or model weights.
Sources
Every paragraph above points to the numbered items it rests on. Read the originals here.
- [1]Meet TokenEconomizer: Microsoft’s Plugin That Cuts Coding Agent Costs by Up to 30.9%MarkTechPost, 4d ago (the report this story comes from)
Background
- [2]Microsoft Word on Wikipedia
- [3]Korean War on Wikipedia
- [4]AI agent on Wikipedia
Our newsroom writes these reports with the help of software, from the 4 sources listed and nothing else, and checks them against those sources. Facts can still be wrong or move on; the originals are the record. Spotted a mistake? Write to daniel@monsterkong.com.
Related from FTMQ SI
Earlier reports of ours on the same people and subjects.
- Google releases Harness2 framework to refine agent software at test timeModels & Products, 16d ago
- Nvidia and AI4Bharat announce multilingual Indic pretraining corpusModels & Products, 18d ago
More in Models & Products
- Apple warns of foldable iPhone Duo supply shortages ahead of holidays6h ago
- Salesforce agrees to acquire customer service startup Cresta for reported 2.7 billion6h ago
- Generative media inference startup fal raises 1.3 billion dollars in new funding6h ago
- Dell and AMD Consolidate Enterprise AI Hardware Into Rack Scale Systems1d ago
- Mistral AI launches Large 4 model for cybersecurity users2d ago
- DeepSeek Open Sources Router Worker Coding Agent Prototype Called dsh superagent2d ago
Get the day in one email
Reports like this one, the top news of the last 24 hours, every morning. Free, one email a day; readers can comment under every report.
By signing up you agree to our terms and privacy policy. Unsubscribe any time.
Comments
Loading
Join the conversation
Comments are open to readers of our daily email: the top news of the last 24 hours, every morning, free. Sign up and the comment box opens.
Already on the list? Enter the same address and we will send a sign-in link.
By signing up you agree to our terms and privacy policy. Unsubscribe any time.