[KongchangAI]
Product

Token Economizer

A context optimization tool released by Microsoft that analyzes repositories and conversation history to automatically identify and remove tool definitions that are never used, reducing the fixed token overhead of coding agents.

Timeline (last 90 days)

Nov 14

All repository information learned by Token Economizer is stored in a local folder and is not uploaded to the cloud, and the project itself is open source.

Unverified50%
Nov 14

Failure-loop intervention uses a separate "judge model" to determine whether the agent is stuck in a repetitive loop, and the judge model only gives hints rather than forcibly terminating the task.

Unverified50%
Nov 14

Token Economizer's benefits depend heavily on repeated sessions on the same repository: the longer it is used and the more it learns, the more it saves; when frequently switching between unrelated projects, the effect is noticeably reduced.

Unverified50%
Nov 14

Each agent learns independently, and what is learned on Claude Code is not automatically transferred to Codex.

Unverified50%
Nov 14

The benefits of micro skills and tool pruning are not linear: savings in the first session are close to zero or even slightly negative, and they usually only become stable after several rounds, or even a dozen or more rounds, of similar tasks.

Unverified50%
Nov 14

Microsoft has open-sourced a free plugin called Token Economizer, used to reduce the token cost of AI coding agents.

Unverified50%
Nov 14

In joint testing by Microsoft and UC Berkeley, Token Economizer reduced the average cost of AI coding agents by 18.4% to about 31%.

Unverified50%
Nov 14

The test covered 6 repositories, 1777 SWE-bench tasks, and 5 agent-and-model combinations, with a per-run cost of about 200 USD.

Unverified50%
Nov 14

Among the 5 agent-and-model combinations, after enabling Token Economizer, the task success rate rose rather than fell in 4 of them and declined slightly in 1.

Unverified50%
Nov 14

In all 30 "repository × agent-model" combinations, enabling the plugin was cheaper than not enabling it.

Unverified50%

8 more timeline events

All Facts (18)

Unverified

All repository information learned by Token Economizer is stored in a local folder and is not uploaded to the cloud, and the project itself is open source.

50%
Unverified

The micro skills feature is disabled by default and must be enabled manually.

50%
Unverified

Failure-loop intervention uses a separate "judge model" to determine whether the agent is stuck in a repetitive loop, and the judge model only gives hints rather than forcibly terminating the task.

50%
Unverified

Token Economizer's benefits depend heavily on repeated sessions on the same repository: the longer it is used and the more it learns, the more it saves; when frequently switching between unrelated projects, the effect is noticeably reduced.

50%
Unverified

Each agent learns independently, and what is learned on Claude Code is not automatically transferred to Codex.

50%
Unverified

The benefits of micro skills and tool pruning are not linear: savings in the first session are close to zero or even slightly negative, and they usually only become stable after several rounds, or even a dozen or more rounds, of similar tasks.

50%
Unverified

In joint testing by Microsoft and UC Berkeley, Token Economizer reduced the average cost of AI coding agents by 18.4% to about 31%.

50%
Unverified

The test covered 6 repositories, 1777 SWE-bench tasks, and 5 agent-and-model combinations, with a per-run cost of about 200 USD.

50%
Unverified

Among the 5 agent-and-model combinations, after enabling Token Economizer, the task success rate rose rather than fell in 4 of them and declined slightly in 1.

50%
Unverified

In all 30 "repository × agent-model" combinations, enabling the plugin was cheaper than not enabling it.

50%
Unverified

Token Economizer's savings figures are net gains, having already deducted the extra model-call overhead required for the plugin itself to run.

50%
Unverified

Token Economizer acts directly on mainstream AI coding agent tools such as Claude Code and Codex, without switching agents or using cheaper models.

50%
Unverified

Token Economizer contains three core mechanisms: micro skills, tool pruning, and failure-loop intervention.

50%
Unverified

In Microsoft's own tests, Token Economizer delivered a cost reduction of 18% to 31%.

50%
Unverified

RTK handles noise on the input side, Caveman handles redundancy on the output side, and Token Economizer handles historical baggage in the context; the three do not replace one another, and only when used together do they cover the complete chain of waste.

50%
Unverified

Token Economizer is a tool developed by Microsoft that learns from the user's repository and past sessions, identifies which tool definitions are almost never called, and trims them from the context.

50%
Unverified

Microsoft has open-sourced a free plugin called Token Economizer, used to reduce the token cost of AI coding agents.

50%
Unverified

Microsoft quietly open-sourced the Cloud Code efficiency plugin Token Economizer, specifically to help Agents reduce Token consumption, supporting Cloud Code, Codex, GitHub Copilot CLI and others.

50%

Source Articles