Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Agentic capability / Self-Operating Computer Framework
◉AgentAgentic capabilityFree

Self-Operating Computer Framework

Framework that lets a multimodal model view the screen and control mouse and keyboard to complete tasks on a computer.

@ai-supply
Installs23k
⟳ upstream v1.5.8 · updated 1y ago
↗ Source repository
← More Agentic capabilityAgentic capability leaderboard →How we grade security →Source ↗
! Grade B · 75/100 · ReviewSecurity assessment
✓No compromise signals7capabilities surfaced1known CVE9of 20 OWASP controls clear
Broad capability surfacePotentially unbounded loopVulnerable dependenciesExternal endpoints declared · expected
scanned 1mo ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

Self-Operating Computer Framework

The Self-Operating Computer Framework lets a multimodal model operate a real computer the way a person does: it captures screenshots, decides what to do, and issues mouse and keyboard actions to accomplish a stated objective. It's a compact, readable reference implementation of the "computer use" pattern that works across multiple vision-capable models.

Key features

  • Screen-perceive → reason → click/type loop driven by a vision LLM
  • Pluggable backends (GPT-4o, Gemini, Claude, LLaVA, and others)
  • Natural-language objectives: "open a browser and search for..."
  • Cross-platform desktop control (macOS, Windows, Linux)
  • Small, hackable codebase for building your own computer-use agent

A concrete starting point for GUI automation and computer-use experiments — useful for testing, repetitive desktop workflows, and research into agents that operate arbitrary software.

Curated mirror of the open-source Self-Operating Computer Framework (MIT). Get it from the source.

Rating rank
#1
of 35 in Agentic capability
Install rank
#34
of 35 in Agentic capability
Security score
75/100 · B
review
Security rank
#22
of 35 in Agentic capability
Installs
23k
cat avg 186k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Agentic capability leaderboard →
! Security: Review · 7575/100 · grade Bscanned 1mo ago
✓ no compromise signals8 risk-surface · 6/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · med confidence (static)
⚑ filesystem⚑ shell⚑ secrets
egress → karpathy.medium.com, platform.openai.com, makersuite.google.com, ai.google.dev, console.anthropic.com, bailian.console.aliyun.com, ollama.ai, www.github.com +8

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 55 pip requirements declared · OthersideAI-self-operating-computer-fac568e/requirements.txtrisk surface
•Vulnerable dependencies — 140 known vulnerabilities in: idna@3.9.0, torch@2.9.1, pillow@10.1.0, aiohttp@3.9.1, certifi@2023.7.22, fonttools@4.44.0, h11@0.14.0, idna@3.4.0 (CWE-1395)known CVE · -25 pts
⚠LLM05Improper Output Handlingmedium
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — OS command execution · OthersideAI-self-operating-computer-fac568e/evaluate.py (CWE-78)expected
⚠LLM06Excessive Agencymedium
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 3 distinct host(s) · OthersideAI-self-operating-computer-fac568e/.gitignoreexpected
•External endpoints declared — 2 distinct host(s) · OthersideAI-self-operating-computer-fac568e/CONTRIBUTING.mdexpected
•External endpoints declared — 13 distinct host(s) · OthersideAI-self-operating-computer-fac568e/README.mdexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · OthersideAI-self-operating-computer-fac568e/evaluate.py (CWE-272)risk surface
•External endpoints declared — 1 distinct host(s) · OthersideAI-self-operating-computer-fac568e/operate/config.pyexpected
⚠LLM10Unbounded Consumptionmedium
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · OthersideAI-self-operating-computer-fac568e/operate/operate.py (CWE-835)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓LLM01Prompt InjectionPassed
✓LLM02Sensitive Information DisclosurePassed
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM07System Prompt LeakagePassed
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML06AI Supply Chaincritical
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 55 pip requirements declared · OthersideAI-self-operating-computer-fac568e/requirements.txtrisk surface
•Vulnerable dependencies — 140 known vulnerabilities in: idna@3.9.0, torch@2.9.1, pillow@10.1.0, aiohttp@3.9.1, certifi@2023.7.22, fonttools@4.44.0, h11@0.14.0, idna@3.4.0 (CWE-1395)known CVE · -25 pts
⚠ML09Output Integritymedium
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — OS command execution · OthersideAI-self-operating-computer-fac568e/evaluate.py (CWE-78)expected
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (2) · hygiene / uncategorized
•Unrecognized file type — '.gitignore' is not on the allowlist · OthersideAI-self-operating-computer-fac568e/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · OthersideAI-self-operating-computer-fac568e/LICENSErisk surface
✔ verified source · pinned OthersideAI-self-operating-computer-fac568e
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/self-operating-computer/check). Click a policy:

Consume Self-Operating Computer Framework programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/self-operating-computer

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/self-operating-computer/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add self-operating-computer

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/self-operating-computer/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "self-operating-computer" })
OpenAPI spec →
vlatest
! Security: Review · 751mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Free, security-vetted AI capabilities — skills, MCPs, plugins, agents, datasets and more, each graded and freshness-tracked, and built for humans and agents alike.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalog
  • Discover
  • Categories
  • Leaderboards
  • Benchmarks
  • Security
  • Scan a repo
Community
  • Community
  • FAQ
For agents
  • Quickstart (60s)
  • Authorize an agent
  • Agent API
  • OpenAPI spec
For builders
  • Publish
  • Dashboard
Account
  • Create account
  • Sign in
  • Settings
Legal
  • Terms
  • Publisher Agreement
  • Acceptable Use
  • Privacy