Skip to content
ai-supply.store
DécouvrirCatégoriesClassementsCommunautéAgent APIFAQ
Se connecterInscription gratuite
catalog / Agentic capability / Basic Memory
◇MCP serverAgentic capabilityFree

Basic Memory

Persistent local Markdown-based memory so your AI assistant remembers across sessions.

@ai-supply
Installations50k
↗ Dépôt source
← More Agentic capabilityAgentic capability leaderboard →How we grade security →Source ↗

Basic Memory

Basic Memory is an open-source Model Context Protocol server that gives AI assistants persistent, local, human-readable memory so you never have to re-explain your project.

Conversations and knowledge are captured as Markdown notes on your own filesystem, forming a connected knowledge base that the assistant can read and write across sessions and tools (Claude, Cursor, and others). Because the notes are plain Markdown, they stay editable and portable outside the AI as well.

It is aimed at people who want durable, ownable long-term memory and knowledge management for their AI workflows.

Rating rank
#1
of 35 in Agentic capability
Install rank
#29
of 35 in Agentic capability
Security score
58/100 · D
review
Security rank
#15
of 35 in Agentic capability
Installs
50k
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 · 5858/100 · grade Dscanned 3h ago
⚠ 1 compromise signal27 risk-surface · 10/20 OWASP controls flagged

Only compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score. Dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to the OWASP control it belongs to below.

What this capability can do · high confidence (static)
Tools (22)
cloud_infolist_memory_projectscreate_memory_projectbm-setuprememberrecallbuild_contextdelete_noteedit_notelist_workspacesmemory_searchmemory_getmove_noteread_noteschema_diffschema_inferschema_validatesearch_noteswrite_notesearchfetchdelete_project
⚑ filesystem⚑ shell⚑ network⚑ secretsinstall: postinstall
egress → huggingface.co, docs.astral.sh, cloud.basicmemory.com, astral.sh, github\.com, api.github.com{path}, api-gateway.umami.dev, pypi.org +10

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.

OWASP Top 10 for LLM Applications
⚠LLM02Sensitive Information Disclosurecompromise · high
Secrets, credentials or PII shipped inside the artifact.
•Embedded credentials — found: DB connection string with credentials · basicmachines-co-basic-memory-39fe75f/.env.example (CWE-798)compromise
•Embedded credentials — found: credentials in URL · basicmachines-co-basic-memory-39fe75f/.github/workflows/release.yml (CWE-798)expected
•Embedded credentials — found: hardcoded credential · basicmachines-co-basic-memory-39fe75f/tests/cli/cloud/test_cloud_api_client_and_utils.py (CWE-798)expected
⚠LLM07System Prompt Leakagecompromise · high
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Embedded credentials — found: DB connection string with credentials · basicmachines-co-basic-memory-39fe75f/.env.example (CWE-798)compromise
•Embedded credentials — found: credentials in URL · basicmachines-co-basic-memory-39fe75f/.github/workflows/release.yml (CWE-798)expected
•Embedded credentials — found: hardcoded credential · basicmachines-co-basic-memory-39fe75f/tests/cli/cloud/test_cloud_api_client_and_utils.py (CWE-798)expected
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · basicmachines-co-basic-memory-39fe75f/tests/utils/test_validate_project_path.py (CWE-200)risk surface
⚠LLM01Prompt Injectionhigh
Adversarial instructions embedded in an artifact that hijack a downstream LLM.
•Prompt-injection phrasing — instruction-subversion language detected · basicmachines-co-basic-memory-39fe75f/tests/repository/test_search_repository.py (CWE-77)expected
⚠LLM03Supply Chainhigh
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 6 npm dependencies declared · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/package.jsonrisk surface
•npm install-lifecycle script — postinstall run on install — executes arbitrary code · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/package.json (CWE-506)risk surface
•Vulnerable dependencies — 63 known vulnerabilities in: pygments@2.9.0, @earendil-works/pi-coding-agent@0.75.5, hono@4.12.23, markdown-it@14.1.1, openclaw@2026.5.26, protobufjs@7.6.1, tar@7.5.13, tar@7.5.15 (CWE-1395)risk surface
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Path traversal sequences — '../' present in content or name · basicmachines-co-basic-memory-39fe75f/.claude/skills/adversarial-review (CWE-22)expected
•Suspicious code patterns — OS command execution · basicmachines-co-basic-memory-39fe75f/benchmarks/src/basic_memory_benchmarks/llm/runners.py (CWE-78)expected
•Suspicious code patterns — destructive rm -rf /; pipe-to-shell install · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/README.md (CWE-78)expected
•Suspicious code patterns — child_process exec · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/SECURITY.md (CWE-78)expected
•Suspicious code patterns — pipe-to-shell install; child_process exec · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/index.ts (CWE-494)expected
•Suspicious code patterns — pipe-to-shell install · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/scripts/setup-bm.sh (CWE-494)expected
•Suspicious code patterns — dynamic code execution · basicmachines-co-basic-memory-39fe75f/src/basic_memory/mcp/ui/html/note-preview-tool-ui.html (CWE-95)expected
•Suspicious code patterns — dynamic os import · basicmachines-co-basic-memory-39fe75f/test-int/test_db_wal_mode.pyexpected
•Suspicious code patterns — OS command execution; dynamic code execution · basicmachines-co-basic-memory-39fe75f/tests/test_codex_plugin_package.py (CWE-78)expected
⚠LLM06Excessive Agencymedium
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · basicmachines-co-basic-memory-39fe75f/.agents/skills/adversarial-review/schemas/findings.schema.jsonexpected
•External endpoints declared — 2 distinct host(s) · basicmachines-co-basic-memory-39fe75f/.agents/skills/instrumentation/SKILL.mdexpected
•External endpoints declared — 3 distinct host(s) · basicmachines-co-basic-memory-39fe75f/.claude/commands/release/release.mdexpected
•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege · basicmachines-co-basic-memory-39fe75f/CHANGELOG.md (CWE-272)risk surface
•External endpoints declared — 15 distinct host(s) · basicmachines-co-basic-memory-39fe75f/README.mdexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · basicmachines-co-basic-memory-39fe75f/benchmarks/src/basic_memory_benchmarks/llm/runners.py (CWE-272)risk surface
•External endpoints declared — 4 distinct host(s) · basicmachines-co-basic-memory-39fe75f/docs/cloud-cli.mdexpected
•External endpoints declared — 6 distinct host(s) · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/.gitignoreexpected
•External endpoints declared — 5 distinct host(s) · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/README.mdexpected
•Broad capability surface — 5 high-impact capability categories referenced — verify least-privilege · basicmachines-co-basic-memory-39fe75f/src/basic_memory/mcp/ui/html/search-results-tool-ui.html (CWE-272)risk surface
⚠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 · basicmachines-co-basic-memory-39fe75f/benchmarks/scripts/write_load_bench.py (CWE-835)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓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.
✓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
⚠ML02Data Poisoninghigh
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
•Prompt-injection phrasing — instruction-subversion language detected · basicmachines-co-basic-memory-39fe75f/tests/repository/test_search_repository.py (CWE-77)expected
⚠ML06AI Supply Chainhigh
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 6 npm dependencies declared · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/package.jsonrisk surface
•npm install-lifecycle script — postinstall run on install — executes arbitrary code · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/package.json (CWE-506)risk surface
•Vulnerable dependencies — 63 known vulnerabilities in: pygments@2.9.0, @earendil-works/pi-coding-agent@0.75.5, hono@4.12.23, markdown-it@14.1.1, openclaw@2026.5.26, protobufjs@7.6.1, tar@7.5.13, tar@7.5.15 (CWE-1395)risk surface
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Path traversal sequences — '../' present in content or name · basicmachines-co-basic-memory-39fe75f/.claude/skills/adversarial-review (CWE-22)expected
•Suspicious code patterns — OS command execution · basicmachines-co-basic-memory-39fe75f/benchmarks/src/basic_memory_benchmarks/llm/runners.py (CWE-78)expected
•Suspicious code patterns — destructive rm -rf /; pipe-to-shell install · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/README.md (CWE-78)expected
•Suspicious code patterns — child_process exec · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/SECURITY.md (CWE-78)expected
•Suspicious code patterns — pipe-to-shell install; child_process exec · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/index.ts (CWE-494)expected
•Suspicious code patterns — pipe-to-shell install · basicmachines-co-basic-memory-39fe75f/integrations/openclaw/scripts/setup-bm.sh (CWE-494)expected
•Suspicious code patterns — dynamic code execution · basicmachines-co-basic-memory-39fe75f/src/basic_memory/mcp/ui/html/note-preview-tool-ui.html (CWE-95)expected
•Suspicious code patterns — dynamic os import · basicmachines-co-basic-memory-39fe75f/test-int/test_db_wal_mode.pyexpected
•Suspicious code patterns — OS command execution; dynamic code execution · basicmachines-co-basic-memory-39fe75f/tests/test_codex_plugin_package.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.
✓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 (11) · hygiene / uncategorized
•Unrecognized file type — '.?' is not on the allowlist · basicmachines-co-basic-memory-39fe75f/.claude/skills/adversarial-reviewrisk surface
•Unrecognized file type — '.dockerignore' is not on the allowlist · basicmachines-co-basic-memory-39fe75f/.dockerignorerisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · basicmachines-co-basic-memory-39fe75f/.gitignorerisk surface
•Unrecognized file type — '.python-version' is not on the allowlist · basicmachines-co-basic-memory-39fe75f/.python-versionrisk surface
•Unrecognized file type — '.cff' is not on the allowlist · basicmachines-co-basic-memory-39fe75f/CITATION.cffrisk surface
•Unrecognized file type — '.coveragerc' is not on the allowlist · basicmachines-co-basic-memory-39fe75f/integrations/hermes/.coveragercrisk surface
•Unrecognized file type — '.ini' is not on the allowlist · basicmachines-co-basic-memory-39fe75f/integrations/hermes/pytest.inirisk surface
•Unrecognized file type — '.mako' is not on the allowlist · basicmachines-co-basic-memory-39fe75f/src/basic_memory/alembic/script.py.makorisk surface
•Unrecognized file type — '.1' is not on the allowlist · basicmachines-co-basic-memory-39fe75f/src/basic_memory/man/basic-memory.1risk surface
•Possible obfuscation — very long lines · basicmachines-co-basic-memory-39fe75f/src/basic_memory/mcp/ui/html/note-preview-tool-ui.htmlrisk surface
•Unrecognized file type — '.hbs' is not on the allowlist · basicmachines-co-basic-memory-39fe75f/src/basic_memory/templates/prompts/continue_conversation.hbsrisk surface
✔ verified source · pinned basicmachines-co-basic-memory-39fe75f
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/basic-memory-mcp/check). Click a policy:

Consume Basic Memory 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/basic-memory-mcp

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

# CLI
npx ai-supply add basic-memory-mcp

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

# MCP tool
install_listing({ "slug": "basic-memory-mcp" })
OpenAPI spec →
vlatest
! Security: Review · 583h 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

Des capacités d'IA gratuites et vérifiées pour la sécurité — skills, MCP, plugins, agents, datasets et bien plus, chacune notée et suivie pour rester à jour, et pensée autant pour les humains que pour les agents.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalogue
  • Découvrir
  • Catégories
  • Classements
  • Benchmarks
  • Sécurité
Communauté
  • Communauté
  • FAQ
Pour les agents
  • Démarrage rapide (60s)
  • Autoriser un agent
  • Agent API
  • Spécification OpenAPI
Pour les développeurs
  • Publier
  • Tableau de bord
Compte
  • Créer un compte
  • Se connecter
  • Paramètres
Mentions légales
  • Conditions
  • Accord éditeur
  • Utilisation acceptable
  • Confidentialité