Hicortex — AI Fleet Memory MCP server
Shared fleet memory for AI agents: nightly self-correction, recall every prompt (supported agents).
2 stars1.3k downloads/wk
Reviews
Write oneNobody has reviewed Hicortex — AI Fleet Memory yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Hicortex — AI Fleet Memory tools (11, 2 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
hicortex_deletewrite actionPermanently delete a memory and its links. Use when a memory is incorrect and should be removed entirely.
hicortex_getFetch ONE memory's full content by id — use this to lazy-load entries from the '## Memory recall (auto)' index or from search results whose snippet was not enough. Fetching a memory marks it as used (strengthens it), so fetch entries that could change your action — not every shown one. When the memory shapes your answer, cite it to the user (id + date + origin agent) — mark a fetched memory `FETCH
hicortex_graphQuery the memory knowledge graph — find connected memories, hub nodes, or paths between memories. Use it to explore memories connected to one you just fetched, or to find hub memories in a domain.
hicortex_identityFetch your standing identity — the hand-edited 'who you are + how you work' layer (personality, rules, preferences). Returns all sections or a specific one. Use this to re-read your identity after context compaction or to look up a specific rule. On multi-agent installs, pass `agent` to fetch a specific agent's scoped identity; omit for the global identity.
hicortex_indexGet the knowledge domain index — shows what topics and projects are stored in memory, grouped by domain. Call before a broad search to see which knowledge domains exist, or when unsure what the memory covers.
hicortex_ingestStore a new memory in long-term storage. Use for Knowledge, Decisions, or Learnings. Capture is automatic (nightly) — use this ONLY for explicitly requested learnings, never routine content.
hicortex_learningsGet actionable Learnings — auto-generated insights about mistakes to avoid. CALL THIS before retrying an approach that failed before, or when picking up work where past problems may have been recorded.
hicortex_lessonsGet actionable Learnings from past sessions — call it before retrying an approach that failed before. (Alias for hicortex_learnings.)
hicortex_recentGet recent memories, optionally filtered by project. CALL THIS AT THE START of substantive work on a project to catch up on its latest state — cheaper than asking the user what happened.
hicortex_searchSearch shared long-term memory (all agents, all sessions). CALL THIS BEFORE assuming, guessing, or asking the user about anything that may have come up before: prior decisions, preferences, project facts, people, hardware, past incidents. If you are about to write 'I don't have information about…', search first.
hicortex_updatewrite actionUpdate an existing memory. Use after searching to fix incorrect information. If content changes, the embedding is re-computed.
Public scan report
scanner v0.1.9 · 2026-09-19 · same rubric, same numbers if you re-run it
- Code scan183 source files scanned8/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 2 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
Findings (2)
- mediumeval / new Function used
exec.evaldist/eval/importance-eval.js: …; /** * Importance-scorer distribution eval (#425) — the AC4 measurement. * * npm…
- highShell command built from a string (injection risk)
exec.shell-concatdist/llm.js: …h try { const raw = execSync(`${claudePath} -p ${JSON.stringify(prompt)} --model ${model} --max-turns 1 --output-format jso…
Grade history
- 2026-09-19restoreD → Cscore 55: Shell command built from a string (injection risk); eval / new Function used
- 2026-09-19restoreF → Dscore 48: Shell command built from a string (injection risk); eval / new Function used; Network call to a raw IP address
Install directly
Runs npx -y @gamaze/hicortex on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add hicortex -- npx -y @gamaze/hicortex
Hicortex — AI Fleet Memory: common questions
- Is Hicortex — AI Fleet Memory MCP server safe?
- With care: it is graded C, so read the findings first (55/100). Read the Hicortex — AI Fleet Memory safety report
- How do I install Hicortex — AI Fleet Memory?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does Hicortex — AI Fleet Memory need an API key?
- Yes. The registry entry asks for
HICORTEX_AUTH_TOKEN. - Is Hicortex — AI Fleet Memory maintained?
- The last commit was 2 days ago (2026-09-17). The latest release is v0.22.0.
- What can I use instead of Hicortex — AI Fleet Memory?
- Servers from other publishers that do the same job: Total Agent Memory MCP server, Fidelis Memory MCP server and Agent Memory Os MCP server. Compare all Hicortex — AI Fleet Memory alternatives.
Alternatives to Hicortex — AI Fleet Memory
Same job from other publishers: the closest match first, then the best rated.
- Total Agent MemoryPersistent local memory for coding agents: temporal knowledge graph, procedural and episodic recallnot reviewedEstablishedA
- Fidelis MemoryRecall locally stored agent memories through an MCP-compatible host.not reviewedGrowingB
- Agent Memory OsLocal-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.not reviewedGrowingA
- IWEMarkdown knowledge base as agent memory. Runs against the notes directory it is started in.not reviewedEstablishedA
- Agent-Native AnalyticsAgent-Native Amplitude/Mixpanel - connect data sources, prompt for chartsnot reviewedEstablishedA