Codex app 100% CPU Usage even when only one agent is running

What version of the Codex App are you using (From “About Codex” dialog)?

Version 26.212.1823 (661)

What subscription do you have?

Plus

What platform is your computer?

Mac OS 26.3

What issue are you seeing?

I am experiencing this issue, only one agents are running right now and see the CPU Usage right now
https://image2url.com/r2/default/images/1771239005182-8a7708b9-5677-4d97-8956-86207364e2c8.png

I am on latest macos version : 26.3
I have Macbook M4 16GB varient

What steps can reproduce the bug?

Open the app and just give any task and the cpu usage will be at 100% right away

What is the expected behavior?

Even when i run many agents to do work it should not take this much cpu usage cause this is happening on cloud.

Additional information

No response

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

macOS App: 100% CPU on Launch and ~60s UI Freeze on Any Interaction (M1 Pro, 32GB, Tahoe 26.1) #11596
Codex desktop app high CPU and rapid memory growth on startup (macOS) #11161
[Bug]: Massive CPU usage (100%+) and overheating (100°C) on M4 Mac Air - Version 260208.1016 #11124
Massive CPU Usage in macOS app #10530
Codex app on MacBook-pro (M4-max) - Massive CPU usage on startup for 55 seconds + Massive performance issues and lag + Response breaking #11584

Powered by Codex Action

@beladiyaraj

@beladiyaraj, are you still seeing this with the latest version of the app? We've fixed a number of performance issues since then. If you're still seeing this, please provide additional details about how we might be able to repro the problem. You mentioned "this is happening in the cloud". Are you saying that you're using a cloud thread (where the tool calls are happening on Codex cloud), or is it a local thread? Are you seeing this with all threads or just some? For example, does it happen only with really long threads?

Having the same issue, syspolicyd spikes at 100 and i can't do anything. Even when i don't do anything, it's still happening.

Observing the same thing that I mentioned in this other issue: #11179 (comment) it sems that Codex is doing posix_spawn on a directory(!) at root of my project (not a binary) repeatedly many times per second and triggering massive syspolicyd cpu spikes.

same situation as in others, latest version

chip: Apple M1 Pro

Adding a correlated data point from local diagnostics (Mar 5, 2026, macOS).

What looks wrong:

CPU is mostly consumed by desktop client processes (Renderer/GPU), not a single backend call.
Symptoms match a cluster of issues tied to:
- long-session renderer growth (#11984, #12709)
- large diff / generated-file tracking pressure (#11861, #11179, #12861)
- heavy local file I/O (#12644)

Local measurements:

Current snapshot: total Codex app CPU ~58%, RSS ~1.3 GB (Renderer + GPU processes dominate).
Earlier today (09:17 session): WARN=6, ERROR=360, ENOENT=339.
Later today (09:56 session): WARN=8, ERROR=14, ENOENT=8.

What improved usage-wise (correlation, not proof):

Keeping active change set smaller,
avoiding large generated/build artifacts in tracked diffs,
restarting into a fresh session when UI starts lagging.

This looks like multiple client-side perf paths rather than one single bug.

@etraut-openai

@etraut-openai I have not encountered this issue after the update has been done

@beladiyaraj

@beladiyaraj, thanks for the confirmation. I'm going to leave this bug open a little longer to wait for confirmation from others who have posted here.

Yes, problem solved and the new model is awesome (GPT-5.4)!

Edit: not solved. Perhaps worktrees cause the issue...after automations have been running...

My mac is boiling running one prompt 🔥

I have that issue when running codex on RustRover on Ubuntu

Have same issue

same issue in apple m3

This Codex overheating issue makes the user experience terrible. And they still haven’t fixed it quickly—seriously speechless.

When I open Codex, there are two Codex Helper Renderer processes, and both hit 100% CPU, even when I’m not doing anything.

I've gone back to the CLI which doesn't have the issue. The x2 usage limit has finished anyway on the app.

…

On Sun, 19 Apr 2026, 12:51 pm zhouqinsong, ***@***.***> wrote: *gitryson* left a comment (openai/codex#11981) <#11981 (comment)> When I open Codex, there are two Codex Helper Renderer processes, and both hit 100% CPU, even when I’m not doing anything. — Reply to this email directly, view it on GitHub <#11981?email_source=notifications&email_token=AAUAM7U3EFL63SCOCLIKS4T4WQ5KDA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTIMRXGUYDGOBVGIZ2M4TFMFZW63VHMNXW23LFNZ2KKZLWMVXHJLDGN5XXIZLSL5RWY2LDNM#issuecomment-4275038523>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAUAM7VSVZWAK232J3DGSSL4WQ5KDAVCNFSM6AAAAACVMLETFCVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHM2DENZVGAZTQNJSGM> . You are receiving this because you commented.Message ID: ***@***.***>

I had this issue for weeks with the vs-code extension. This worked for me

https://github.com/jxhnx/codex/tree/fix/code-extension-cpu-regression/patches/openai-chatgpt-vscode-extension-26.5415.20818-broadcast-warning-hotfix

Pinned to a recent version. No guarantees. Platform macOS Tahoe 26.4.1.

Same on Windows... the perf of the desktop app is horrible. The only reason I don't recommend it to more people.

My feedback id if it helps:
d1467c55-28f3-4c72-954c-e3331663e76c

I had this issue for weeks with the vs-code extension. This worked for me

https://github.com/jxhnx/codex/tree/fix/code-extension-cpu-regression/patches/openai-chatgpt-vscode-extension-26.5415.20818-broadcast-warning-hotfix

Pinned to a recent version. No guarantees. Platform macOS Tahoe 26.4.1.

Just did this, didn't do anything for me.

Edit: Actually, the CPU usage is still high but my Mac isn't making as much noise. Progress I think?

Edit 2: Nah, still the same thing.

Figured out that using Codex (beta).app makes the cpu and gpu usage about 30-35% less than with the main app. Worth it for now.

Got the same problem for few weeks, now just open codex app makes my Mac overheated. No agents are running, simply open it. M4 chip with 24Gb ram, sequoia 15.4.1. Codex 26.422.30944 (2080)

Got the same problem for few weeks, now just open codex app makes my Mac overheated. No agents are running, simply open it. M4 chip with 24Gb ram, sequoia 15.4.1. Codex 26.422.30944 (2080)

I coded my own codex app. Its 9x more cpu efficient. No heating, no jet engine sound, super smooth. Highly recommend.

High CPU usage with a single agent is usually caused by one of three things in agent architectures:

Polling loops without backoff: The agent loop polls for state changes (file system events, model responses, background tasks) at maximum frequency instead of using event-driven notifications. This consumes 100% of one CPU core even when idle.
Context window management thrashing: When context approaches the window limit, the system enters a compact-expand cycle. It compacts context to free space, which triggers a state recalculation, which expands context again, which triggers compaction. We see this in our multi-agent deployment when the compaction threshold is too close to the context limit.
Unbounded memory growth leading to GC pressure: Agent state (conversation history, tool results, cached embeddings) grows over time. Without proactive cleanup, the garbage collector runs continuously trying to free memory, consuming CPU.

What we do to keep agents efficient:

Event-driven agent loop: The agent sleeps until there is work to do (user message, tool result, timer event). No polling. CPU usage is near zero when idle.
Progressive compaction with hysteresis: Compact when context reaches 75% of limit. Do not re-expand until context drops below 60%. The 15% gap prevents the compact-expand thrashing cycle.
Per-agent resource budgets: Each agent has a CPU time limit per turn. If a single reasoning step exceeds the limit, it is interrupted and the agent reports partial results. This prevents one complex prompt from monopolizing the CPU.
Memory management: Tool results are compacted after processing (full result compressed to structured summary). Working memory is bounded with an LRU eviction policy.

Context management architecture: https://blog.kinthai.ai/why-character-ai-forgets-you-persistent-memory-architecture

Multi-agent resource governance: https://blog.kinthai.ai/openclaw-multi-tenancy-why-vm-per-user-doesnt-scale

Found the problem for me and a workaround in #20213

Really want to use Codex app but keep going back to the CLI as the performance is just crazy still

Macbook(M4 pro with 48G ram, sequoia 15.6.1). Just open Codex(Version 26.506.31421 (2620)) with a chat, cpu usage raise to 200% and always keep the weird status unless I quit the app😭

the original reporter confirmed this was resolved after an app update

this thread now combines several unrelated cpu reports, and we’re trying to avoid overly broad bucketing issues like this and focus only on issues with strong repros

please file new issues and include current version, affected process, and repro steps when unexpected high cpu still occurs

Navigation Menu

Repository navigation

Codex app 100% CPU Usage even when only one agent is running #11981

What version of the Codex App are you using (From “About Codex” dialog)?

What subscription do you have?

What platform is your computer?

What issue are you seeing?

What steps can reproduce the bug?

What is the expected behavior?

Additional information

24 remaining items

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Codex app 100% CPU Usage even when only one agent is running #11981

Description

What version of the Codex App are you using (From “About Codex” dialog)?

What subscription do you have?

What platform is your computer?

What issue are you seeing?

What steps can reproduce the bug?

What is the expected behavior?

Additional information

Activity

github-actions commented on Feb 17, 2026

etraut-openai commented on Feb 24, 2026

lordsoffallen commented on Feb 24, 2026

pllopis commented on Feb 26, 2026

whitemankpi commented on Feb 26, 2026

DigitarInt commented on Mar 5, 2026

beladiyaraj commented on Mar 5, 2026

etraut-openai commented on Mar 5, 2026

DigitarInt commented on Mar 6, 2026

rob-balfre commented on Mar 8, 2026

stanedgar6 commented on Mar 8, 2026

nezzard commented on Mar 9, 2026

TestMsr commented on Mar 11, 2026

24 remaining items

gitryson commented on Apr 19, 2026

gitryson commented on Apr 19, 2026

rob-balfre commented on Apr 19, 2026

jxhnx commented on Apr 19, 2026

mrairdon-midmark commented on Apr 25, 2026

oimrqs-ops commented on Apr 25, 2026

oimrqs-ops commented on Apr 26, 2026

ptoyip commented on Apr 28, 2026

oimrqs-ops commented on Apr 28, 2026

kinthaiofficial commented on Apr 28, 2026

mrairdon-midmark commented on May 1, 2026

rob-balfre commented on May 5, 2026

tomleader commented on May 9, 2026

chess-oai commented on Aug 15, 2026

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions