Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Agentic capability / Basic Memory
◇MCP serverAgentic capabilityFree

Basic Memory

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

@ai-supply
Installs50k
↗ Source repository
← 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 2h ago

Only compromise signals — malicious or tampered code (leaked secrets, backdoors, path traversal, a dropped executable) — reduce the score. Dangerous-by-capability traits (shell, network, injection strings, pickle) are shown as risk surface: expected for some capabilities — a security tool ships offensive code on purpose — so they do not sink the grade.

Compromise signals
Embedded credentialshighbasicmachines-co-basic-memory-39fe75f/.env.example
found: DB connection string with credentials
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
Risk surface (27)
External endpoints declaredlowexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/.agents/skills/adversarial-review/schemas/findings.schema.json
1 distinct host(s)
External endpoints declaredlowexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/.agents/skills/instrumentation/SKILL.md
2 distinct host(s)
External endpoints declaredlowexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/.claude/commands/release/release.md
3 distinct host(s)
Path traversal sequencesmediumexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/.claude/skills/adversarial-review
'../' present in content or name
Embedded credentialshighexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/.github/workflows/release.yml
found: credentials in URL
Broad capability surfacelowbasicmachines-co-basic-memory-39fe75f/CHANGELOG.md
4 high-impact capability categories referenced — verify least-privilege
External endpoints declaredmediumexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/README.md
15 distinct host(s)
Potentially unbounded loopmediumbasicmachines-co-basic-memory-39fe75f/benchmarks/scripts/write_load_bench.py
an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption
Suspicious code patternsmediumexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/benchmarks/src/basic_memory_benchmarks/llm/runners.py
OS command execution
Broad capability surfacelowbasicmachines-co-basic-memory-39fe75f/benchmarks/src/basic_memory_benchmarks/llm/runners.py
3 high-impact capability categories referenced — verify least-privilege
External endpoints declaredlowexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/docs/cloud-cli.md
4 distinct host(s)
External endpoints declaredlowexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/integrations/openclaw/.gitignore
6 distinct host(s)
Suspicious code patternshighexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/integrations/openclaw/README.md
destructive rm -rf /; pipe-to-shell install
External endpoints declaredlowexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/integrations/openclaw/README.md
5 distinct host(s)
Suspicious code patternsmediumexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/integrations/openclaw/SECURITY.md
child_process exec
Suspicious code patternshighexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/integrations/openclaw/index.ts
pipe-to-shell install; child_process exec
npm install-lifecycle scripthighbasicmachines-co-basic-memory-39fe75f/integrations/openclaw/package.json
postinstall run on install — executes arbitrary code
Suspicious code patternshighexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/integrations/openclaw/scripts/setup-bm.sh
pipe-to-shell install
Suspicious code patternsmediumexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/src/basic_memory/mcp/ui/html/note-preview-tool-ui.html
dynamic code execution
Possible obfuscationmediumbasicmachines-co-basic-memory-39fe75f/src/basic_memory/mcp/ui/html/note-preview-tool-ui.html
very long lines
Broad capability surfacelowbasicmachines-co-basic-memory-39fe75f/src/basic_memory/mcp/ui/html/search-results-tool-ui.html
5 high-impact capability categories referenced — verify least-privilege
Suspicious code patternsmediumexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/test-int/test_db_wal_mode.py
dynamic os import
Embedded credentialshighexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/tests/cli/cloud/test_cloud_api_client_and_utils.py
found: hardcoded credential
Prompt-injection phrasinghighexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/tests/repository/test_search_repository.py
instruction-subversion language detected
Suspicious code patternsmediumexpected for this capabilitybasicmachines-co-basic-memory-39fe75f/tests/test_codex_plugin_package.py
OS command execution; dynamic code execution
Internal host / private infrastructure referencemediumbasicmachines-co-basic-memory-39fe75f/tests/utils/test_validate_project_path.py
shipped content references a private IP range or internal-only host
Vulnerable dependencieshigh
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
✔ 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:

OWASP AI control mapping
5passed
10flagged
0runtime-enforced
5governance

Evaluated against the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any control to see the findings.

OWASP Top 10 for LLM Applications
⚠LLM01Prompt Injectionhigh
Adversarial instructions embedded in an artifact that hijack a downstream LLM.
•Prompt-injection phrasing — instruction-subversion language detected (CWE-77)
⚠LLM02Sensitive Information Disclosurehigh
Secrets, credentials or PII shipped inside the artifact.
•Embedded credentials — found: DB connection string with credentials (CWE-798)
•Embedded credentials — found: credentials in URL (CWE-798)
•Embedded credentials — found: hardcoded credential (CWE-798)
⚠LLM03Supply Chainhigh
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 6 npm dependencies declared
•npm install-lifecycle script — postinstall run on install — executes arbitrary code (CWE-506)
•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)
✓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.
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Path traversal sequences — '../' present in content or name (CWE-22)
•Suspicious code patterns — OS command execution (CWE-78)
•Suspicious code patterns — destructive rm -rf /; pipe-to-shell install (CWE-78)
•Suspicious code patterns — child_process exec (CWE-78)
•Suspicious code patterns — pipe-to-shell install; child_process exec (CWE-494)
•Suspicious code patterns — pipe-to-shell install (CWE-494)
•Suspicious code patterns — dynamic code execution (CWE-95)
•Suspicious code patterns — dynamic os import
•Suspicious code patterns — OS command execution; dynamic code execution (CWE-78)
⚠LLM06Excessive Agencymedium
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s)
•External endpoints declared — 2 distinct host(s)
•External endpoints declared — 3 distinct host(s)
•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege (CWE-272)
•External endpoints declared — 15 distinct host(s)
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege (CWE-272)
•External endpoints declared — 4 distinct host(s)
•External endpoints declared — 6 distinct host(s)
•External endpoints declared — 5 distinct host(s)
•Broad capability surface — 5 high-impact capability categories referenced — verify least-privilege (CWE-272)
⚠LLM07System Prompt Leakagehigh
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Embedded credentials — found: DB connection string with credentials (CWE-798)
•Embedded credentials — found: credentials in URL (CWE-798)
•Embedded credentials — found: hardcoded credential (CWE-798)
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host (CWE-200)
✓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.
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
⚠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 (CWE-835)
OWASP Machine Learning Security Top 10
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
⚠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 (CWE-77)
§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.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
⚠ML06AI Supply Chainhigh
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 6 npm dependencies declared
•npm install-lifecycle script — postinstall run on install — executes arbitrary code (CWE-506)
•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)
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
⚠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 (CWE-22)
•Suspicious code patterns — OS command execution (CWE-78)
•Suspicious code patterns — destructive rm -rf /; pipe-to-shell install (CWE-78)
•Suspicious code patterns — child_process exec (CWE-78)
•Suspicious code patterns — pipe-to-shell install; child_process exec (CWE-494)
•Suspicious code patterns — pipe-to-shell install (CWE-494)
•Suspicious code patterns — dynamic code execution (CWE-95)
•Suspicious code patterns — dynamic os import
•Suspicious code patterns — OS command execution; dynamic code execution (CWE-78)
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.

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 · 582h 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
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