HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
pig-dot-dev
muscle-mem
Python2025–2025
pig-dot-dev / muscle-mem

muscle-mem

A cache for AI agents to learn and replay complex behaviors.

Learning & ReferenceAI & Machine Learning
Explore on GitHubRead Hacker News discussions
2Distinct people
2Mentions
0Explicit recommenders
765GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

A cache for AI agents to learn and replay complex behaviors.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by 3-hour interval2 dated mentions

Observed mentions: 2025-05-14 19:38:26 UTC to 2025-05-17 09:38:34 UTC.

012025-05-14 18:00:00 UTC to 2025-05-14 21:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsMay 14, 18:002025-05-14 21:00:00 UTC to 2025-05-15 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-15 00:00:00 UTC to 2025-05-15 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-15 03:00:00 UTC to 2025-05-15 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-15 06:00:00 UTC to 2025-05-15 09:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-15 09:00:00 UTC to 2025-05-15 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-15 12:00:00 UTC to 2025-05-15 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-15 15:00:00 UTC to 2025-05-15 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-15 18:00:00 UTC to 2025-05-15 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-15 21:00:00 UTC to 2025-05-16 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-16 00:00:00 UTC to 2025-05-16 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsMay 16, 00:002025-05-16 03:00:00 UTC to 2025-05-16 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-16 06:00:00 UTC to 2025-05-16 09:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-16 09:00:00 UTC to 2025-05-16 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-16 12:00:00 UTC to 2025-05-16 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-16 15:00:00 UTC to 2025-05-16 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-16 18:00:00 UTC to 2025-05-16 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-16 21:00:00 UTC to 2025-05-17 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-17 00:00:00 UTC to 2025-05-17 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-17 03:00:00 UTC to 2025-05-17 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-17 06:00:00 UTC to 2025-05-17 09:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-05-17 09:00:00 UTC to 2025-05-17 12:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsMay 17, 09:00

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
May 14, 18:002025-05-14 18:00:00 UTC2025-05-14 21:00:00 UTC110
May 14, 21:002025-05-14 21:00:00 UTC2025-05-15 00:00:00 UTC000
May 15, 00:002025-05-15 00:00:00 UTC2025-05-15 03:00:00 UTC000
May 15, 03:002025-05-15 03:00:00 UTC2025-05-15 06:00:00 UTC000
May 15, 06:002025-05-15 06:00:00 UTC2025-05-15 09:00:00 UTC000
May 15, 09:002025-05-15 09:00:00 UTC2025-05-15 12:00:00 UTC000
May 15, 12:002025-05-15 12:00:00 UTC2025-05-15 15:00:00 UTC000
May 15, 15:002025-05-15 15:00:00 UTC2025-05-15 18:00:00 UTC000
May 15, 18:002025-05-15 18:00:00 UTC2025-05-15 21:00:00 UTC000
May 15, 21:002025-05-15 21:00:00 UTC2025-05-16 00:00:00 UTC000
May 16, 00:002025-05-16 00:00:00 UTC2025-05-16 03:00:00 UTC000
May 16, 03:002025-05-16 03:00:00 UTC2025-05-16 06:00:00 UTC000
May 16, 06:002025-05-16 06:00:00 UTC2025-05-16 09:00:00 UTC000
May 16, 09:002025-05-16 09:00:00 UTC2025-05-16 12:00:00 UTC000
May 16, 12:002025-05-16 12:00:00 UTC2025-05-16 15:00:00 UTC000
May 16, 15:002025-05-16 15:00:00 UTC2025-05-16 18:00:00 UTC000
May 16, 18:002025-05-16 18:00:00 UTC2025-05-16 21:00:00 UTC000
May 16, 21:002025-05-16 21:00:00 UTC2025-05-17 00:00:00 UTC000
May 17, 00:002025-05-17 00:00:00 UTC2025-05-17 03:00:00 UTC000
May 17, 03:002025-05-17 03:00:00 UTC2025-05-17 06:00:00 UTC000
May 17, 06:002025-05-17 06:00:00 UTC2025-05-17 09:00:00 UTC000
May 17, 09:002025-05-17 09:00:00 UTC2025-05-17 12:00:00 UTC101

What Hacker News says

2 sources
edunteman·May 14, 2025Submission

Show HN: Muscle-Mem, a behavior cache for AI agents

Hi HN! Erik here from Pig.dev, and today I'd like to share a new project we've just open sourced: Muscle Mem is an SDK that records your agent's tool-calling patterns as it solves tasks, and will deterministically replay those learned trajectories whenever the task is encountered again, falling back to agent mode if edge cases are detected. Like a JIT compiler, for behaviors. At Pig, we built computer-use agents for automating legacy Windows applications (healthcare, lending, manufacturing, etc). A recurring theme we ran into was that businesses already had RPA (pure-software scripts), and it worked for them in most cases. The pull to agents as an RPA alternative was not to have an infinitely flexible "AI Employees" as tech Twitter/X may want you to think, but simply because their RPA breaks under occasional edge-cases and agents can grac
Read the rest
efully handle those cases. Using a pure-agent approach proved to be highly wasteful. Window's accessibility APIs are poor, so you're generally stuck using pure-vision agents, which can run around $40/hr in token costs and take 5x longer than a human to perform a workflow. At this point, you're better off hiring a human. The goal of Muscle-Mem is to get LLMs out of the hot path of repetitive automations, intelligently swapping between script-based execution for repeat cases, and agent-based automations for discovery and self-healing. While inspired by computer-use environments, Muscle Mem is designed to generalize to any automation performing discrete tasks in dynamic environments. It took a great deal of thought to figure out an API that generalizes, which I cover more deeply in this blog: https://erikdunteman.com/blog/muscle-mem/ Check out the repo, consider giving it a star, or dive deeper into the above blog. I look forward to your feedback!
226 points · Open discussion

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.