CogmemAi — Cognitive Memory for Any Ai System

Autonomous robots. Self-driving vehicles. Defense systems. Coding assistants. Any Ai system that needs to remember.

CogmemAi is a portable memory layer that gives any Ai system persistent recall across sessions, devices, users, and teams — and captures knowledge autonomously, even when your Ai forgets to save. 95.10% accuracy on LongMemEval — top published score on the field's hardest long-term memory benchmark. 91% on LoCoMo, above human performance (87.9%). Quantum-safe encryption. Works with Claude Code, Cursor, Windsurf, Cline, Continue, and any MCP-compatible tool. Switch editors, switch models, switch machines — your knowledge stays. Not just one score on a test — the most complete Ai memory system available.

What's New in v3

CogmemAi Guard: Your Memory Now Stops Your Ai From Repeating Mistakes (v3.24.0)

Memory that only advises is memory your Ai can ignore under pressure. v3.24.0 adds a guard that turns what your project remembers into enforcement.

A PreToolUse hook judges every shell command before it runs. Six built-in rules cover the operations with no good unattended use: rewriting a whole crontab from a pipeline, destructive SQL against a live database, recursive deletes outside temp and build paths, force-pushing to a shared branch, piping a download into a shell, and killing shared server workers by name. The same rules are applied to what a command carries inside ssh host "...", bash -c "...", and a heredoc fed to a shell, because that payload runs on the far side exactly as written.

Then the part only a memory layer can do. Rule memories you save with save_rule become enforceable patterns. Write NEVER run \pkill -u www lsphp`in a rule and the next session denies that command, over ssh too, with the rule's own words as the reason. No code to edit. Add aGUARD: line to a rule for an exact pattern, orGUARD: off` to keep a rule advisory.

A Stop hook reviews what actually changed at the end of each turn: credentials pasted into tracked source, version strings that disagree across release files, deleted files, large net deletions, a function now defined in two places, and remembered gotchas about the files that were touched. It reports; it never edits.

Every verdict is logged locally with secrets redacted, so precision is measured rather than assumed. Denials name the deliberate path forward, usually "run it yourself". The guard fails open on any error, and git remains the real undo. See Guard below.

v3.25.0 extends it past Claude Code: guard shell-install hooks every bash -c and zsh -c on the machine through BASH_ENV, so Cursor, Codex, Gemini CLI, and plain scripts get the same guard, the same remembered rules, and the same log.

Loud Failures on Firewall Blocks (v3.20.0)

When a request to the CogmemAi backend is intercepted by an upstream firewall, CDN, or proxy, the response is HTML, not JSON. Earlier versions tried to JSON-parse it and threw a confusing Unexpected token '<' error, then silently retried the same blocked payload. v3.20.0 detects HTML responses, names the blocking layer when it can (NinjaFirewall, Cloudflare, ModSecurity), and surfaces a clear actionable error. Retryable 4xx responses with HTML bodies no longer trigger retry loops. The class of incident that can silently drop memory writes is now loud.

Autonomous Memory — Your Ai Doesn't Decide Whether to Save Anymore (v3.15)

Every memory system has the same hidden failure mode: the Ai has to choose to save, and under pressure it doesn't. You can bake instructions into system prompts. You can nudge. But when your Ai is head-down on a coding task, it forgets to save — and the decisions you made two hours ago vanish when the context compacts.

CogmemAi v3.15 moves the decision out of the Ai's hands entirely. Your coding sessions are captured at the infrastructure level — decisions, file changes, bug fixes, and deployments land in memory without a single prompt. At session end, an intelligence pass distills them into structured memories: the right types, the right importance scores, the right scopes. Your Ai never sees this happen.

The result: a day of heavy coding produces 15–20 quality memories instead of 3. Future sessions pick up seamlessly. Your Ai stops re-litigating architectural choices you already made. Stop reminding your Ai to remember. It just does.

Proactive Memory Recall (v3.12)

CogmemAi now thinks before it speaks. Before your Ai assistant suggests any action, approach, or recommendation, CogmemAi checks its memory first — automatically, on every topic.

• preflight tool — A fast, lightweight recall designed to be called before every suggestion. Your assistant checks what it already knows about a topic before opening its mouth. "Let's try approach X" → first checks if X was already tried, rejected, or completed. Sub-200ms, near-zero cost.
• Prior context surfacing — Every time a memory is saved, CogmemAi automatically searches for related prior memories across all topics — people, companies, technical approaches, features, everything — and surfaces them in the response. Your assistant never suggests something redundant.
• Smart recall hooks — In Claude Code, CogmemAi reads every user message and automatically injects relevant memories before the assistant responds. No manual recall needed — context arrives before the assistant starts thinking.
• Upgraded recall engine — Higher-dimensional semantic understanding, balanced reranking, keyword-expanded search, dual-path memory storage for more reliable retrieval, and adaptive search that expands automatically when initial results are low confidence.

The result: your Ai assistant stops suggesting things you've already tried, people you've already contacted, and approaches you've already rejected. Your brain is no longer the safety net for what your tools should already know.

Wisdom Engine — Auto-Extracted Principles (v3.10)

CogmemAi now automatically detects patterns across your memories and extracts factual principles. While skills tell your Ai HOW to behave ("always use Zustand"), principles tell it what's TRUE about your project ("this codebase never validates inputs at service boundaries"). Principles are extracted from clusters of 5+ related memories, scored by confidence, and injected into every session. Use extract_principles to trigger manually or let it happen automatically.

Remote MCP — Zero Install (v3.9)

CogmemAi now supports Streamable HTTP transport — connect from any MCP client without installing anything. No npm, no config files, no Node.js required. Just point your client to https://hifriendbot.com/mcp/ with your API key and start using persistent memory immediately. Same 35 tools, same Intelligence Engine, same benchmark-topping accuracy — zero setup friction.

Quantum-Safe Encryption (v3.7)

CogmemAi is the first quantum-safe Ai memory system. All memories are encrypted at rest with quantum-resistant encryption — both in cloud mode and local mode. Your data is protected against today's threats and tomorrow's quantum computers. Encryption is automatic, zero-config, and enabled by default. No setup required.

Choose Your Storage Mode (v3.6)

CogmemAi now runs three ways — pick the one that fits your workflow:

	Cloud (default)	Local	Hybrid
Best for	Full intelligence, team collaboration, cross-device portability	Zero-config start, offline-only environments	Local speed + cloud brains, travel/unreliable networks
Setup	npx cogmemai-mcp setup (choose Cloud)	npx cogmemai-mcp setup (choose Local)	npx cogmemai-mcp setup (choose Hybrid)
API key needed	Yes (free)	Yes (free) — like a license key, your data stays local	Yes (free)
Search	Semantic (by meaning)	Full-text search (FTS5)	Semantic with local fallback
Intelligence Engine	Full — auto-linking, contradiction detection, memory decay, auto-skills, query synthesis	FTS5 search + CRUD — data stays on your machine	Full — with offline resilience
Team collaboration	Yes	No	Yes
Cross-device sync	Automatic	No — data stays on your machine	Automatic with local cache
Offline support	Requires internet	Full offline	Falls back to local when offline
Encryption	Quantum-safe (server)	Quantum-safe (local)	Quantum-safe (both)

Cloud mode is the recommended experience. It gives you the full Intelligence Engine — semantic search that finds memories by meaning, auto-linking knowledge graph, contradiction detection, self-improving recall, auto-skills, query synthesis, and team collaboration. Everything that makes CogmemAi more than just a database.

Local mode keeps your data on your machine. A free API key is required for registration (like a software license key), but all your data stays local. Full-text search (FTS5) provides quality recall. Works offline after initial setup. When you're ready for semantic search and the full Intelligence Engine, upgrading to cloud takes one command.