Repository navigation
Codex memory grows to 75GB+ during basic session #20740
Description
Summary
Urgent: Codex can grow to extreme memory usage during an apparently basic/single-task session, eventually triggering macOS "Your system has run out of application memory."
Observed in the macOS Force Quit Applications dialog:
Codex: 75.50 GB
cmux (paused): 10.76 GB
Activity Monitor: 60.4 MB
Finder: 125.9 MB
The memory usage reportedly kept increasing and reached roughly 85 GB before Codex was stopped to avoid taking down the system.
Environment
- Codex CLI:
codex-cli 0.128.0 - OS: macOS 26.4.1, Darwin 25.4.0, arm64
- Model:
gpt-5.5 - Reasoning effort:
medium - Config has
multi_agent = true, but the observed problem happened during a basic/single-task session, not an intentionally large multi-agent run.
Impact
This is system-threatening on macOS:
- macOS showed the global "system has run out of application memory" dialog.
- Codex reached at least 75.50 GB in the Force Quit dialog.
- The user had to stop Codex manually when it approached roughly 85 GB and was still increasing.
- This can interrupt work and risks destabilizing the whole machine.
What happened
During a normal Codex session, memory usage climbed continuously even though the user was not running a large task. The behavior looked like runaway accumulation/leak rather than a bounded memory spike.
Relevant local log clue from the same timeframe:
turn{... model=gpt-5.5 codex.turn.token_usage.input_tokens=1905121 ... codex.turn.token_usage.cached_input_tokens=1818240 ... codex.turn.token_usage.non_cached_input_tokens=86881 ... codex.turn.token_usage.output_tokens=3950 ... codex.turn.token_usage.reasoning_output_tokens=1091 ... codex.turn.token_usage.total_tokens=1909071}: codex_core::tasks: close time.busy=1.18s time.idle=361s
That is about 1.9M total tokens for a session that did not feel like a large task from the user's perspective. This may indicate that Codex is retaining/re-sending/accumulating too much session context or cached input state across turns, which may correlate with the memory growth.
Expected behavior
For a basic single-task session, Codex memory should remain bounded and should not grow into tens of GB. If a session/context grows unexpectedly large, Codex should either compact, evict, fail fast with a clear diagnostic, or provide an explicit warning before the desktop app threatens system memory.
Actual behavior
Codex memory kept increasing until macOS forced the user into the application memory pressure dialog. Codex was shown at 75.50 GB and was reportedly near 85 GB before the user stopped it.
Notes
This may be related to a separate WebSocket/Responses streaming instability issue already filed here:
However, this issue is distinct: the urgent failure here is unbounded memory growth / excessive retained context during ordinary usage.
Activity
github-actions commentedon May 2, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
[-]Urgent: Codex memory grows to 75GB+ during basic session[/-][+]Codex memory grows to 75GB+ during basic session[/+]dpandey82 commentedon May 5, 2026
I faced same issue on my macbook m3pro
mistersilver-uk commentedon May 5, 2026
I've experienced the same issue on Ubuntu.
IgorGanapolsky commentedon May 6, 2026
I hit a very similar macOS failure mode while cleaning up a local multi-project agent workstation. The useful distinction was separating Codex memory growth from session-restore amplification.
A few diagnostics that made the issue easier to reason about:
The mitigation that stopped the machine-wide collapse was:
This does not prove the root cause inside Codex, but it prevents a single leak/regression from being multiplied by restored sessions and background launch jobs.
I wrote up the operational checklist here in case it helps other macOS users debug safely without wiping their workspace: https://igorganapolsky.github.io/AI_OpenClaw_Setup_Kits/guides/codex-openclaw-runaway-agent-safety.md
omry commentedon May 15, 2026
For WSL / Ubuntu users hitting this class of memory growth, I posted a containment workaround here: #18041 (comment)
Short version: use the VS Code extension setting
chatgpt.cliExecutableto point at a wrapper that launches the bundled native Codex binary throughsystemd-run --user --scopewithMemoryMax/MemorySwapMax.This does not fix the leak, but it prevents Codex from taking down the whole WSL VM or Linux desktop.
tui: free event buffers for closed background agent threads