prism-coder
Health Pass
- License — License: NOASSERTION
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Community trust — 132 GitHub stars
Code Pass
- Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
- Permissions — No dangerous permissions requested
This tool is a Model Context Protocol (MCP) server that provides persistent, long-term memory for AI agents. It allows AI assistants to remember context across sessions using a local "Mind Palace" architecture with semantic search and cognitive routing.
Security Assessment
Risk Rating: Low
The automated code scan checked 12 files and found no dangerous patterns, hardcoded secrets, or requests for dangerous permissions. The server runs locally using an onboard LLM and SQLite, meaning no external API keys are required for the free tier. While the tool processes conversational data, it keeps this sensitive information on your device by default. Users should note that a paid tier exists which introduces cloud sync, but the base local installation avoids network transmission. No hidden shell command executions were detected.
Quality Assessment
This is an actively maintained project, with its last code push occurring today. It has solid community trust for a niche tool, currently backed by 132 GitHub stars. Furthermore, it is officially listed in the MCP Registry and on Smithery, indicating it meets broader ecosystem standards. However, there is a minor discrepancy in the health checks: the automated scan detected the license as "NOASSERTION," while the README explicitly states it uses the "BUSL-1.1" license. Developers should be aware that the Business Source License (BUSL-1.1) has specific restrictions regarding commercial use and production deployments, meaning it is not a standard open-source license like MIT.
Verdict
Safe to use locally, but review the BUSL-1.1 license terms if you plan to use this in a commercial or production environment.
The Mind Palace for AI Agents - HIPAA-hardened Cognitive Architecture with on-device LLM (prism-coder:7b), Hebbian learning, ACT-R spreading activation, adversarial evaluation, persistent memory, multi-agent Hivemind and visual dashboard. Zero API keys required.
🧠 Prism MCP
Persistent memory for AI agents.
A Model Context Protocol server that gives Claude, Cursor, and other AI tools a Mind Palace — long-term memory that survives across sessions, with semantic search, cognitive routing, and a visual dashboard.
🌐 Translations: Español · Français · Português · Română · Українська · Русский · Deutsch · 日本語 · 한국어 · 中文 · العربية
What Prism does
💾 Your AI remembers across sessions
Every conversation feeds the Mind Palace. Next session, your AI agent loads the right context automatically — no re-explaining.
🔍 Semantic search over your history
Ask "what did I decide about the auth flow last month?" and get the answer with citations. Vector search + keyword + graph traversal.
🧬 Cognitive routing
Different memory types live in different stores: episodic (what happened), semantic (what's true), procedural (how to do X). The router picks where to store and where to retrieve.
🛡 Local-first
Free tier runs entirely on your machine — SQLite, local embedding model, no API keys, no cloud. Paid tier adds cloud sync via Synalux portal.
⚡ Zero-search retrieval
Holographic Reduced Representations (HRR) for instant similarity lookups without an index. ~5ms over 100K memories.
🌐 Multi-agent Hivemind
Multiple AI agents share the same Mind Palace. Each agent has a role (dev / qa / pm / etc.) and sees scoped context. Heartbeat + roster for coordination.
Get started
# Install globally
npm install -g prism-mcp-server
# Or use npx (no install)
npx prism-mcp-server
Add to Claude Desktop / Cursor config:
{
"mcpServers": {
"prism": {
"command": "npx",
"args": ["-y", "prism-mcp-server"]
}
}
}
That's it. Open Claude / Cursor and your AI now has memory.
More setup details in docs/SETUP_GEMINI.md.
How AI agents use it
| Tool | What it does |
|---|---|
session_load_context |
Recover prior session's state on boot |
session_save_ledger |
Append immutable session log entry |
session_save_handoff |
Save live state for the next session |
knowledge_search |
Semantic + keyword search over all memories |
query_memory_natural |
Natural-language Q&A over your Mind Palace |
extract_entities |
Pull people / projects / decisions from text |
session_synthesize_edges |
Auto-link related memories into a graph |
(35+ tools total — full TypeScript signatures in src/tools/. Architecture overview in docs/ARCHITECTURE.md.)
Plans
| Free (local) | Paid (Synalux portal) | |
|---|---|---|
| Local SQLite memory | ✅ | ✅ |
| Semantic search | ✅ (local embedding) | ✅ (cloud-backed) |
| Cross-device sync | — | ✅ |
| Hivemind multi-agent | ✅ local team | ✅ + cloud roster |
| Auto-Scholar (web research → memory) | — | ✅ |
| HRR Zero-Search retrieval | ✅ | ✅ |
| Custom domains / SSO | — | Enterprise |
The thin-client architecture: when authenticated to Synalux, prism-mcp routes through the portal for paid features. When not authenticated (or PRISM_FORCE_LOCAL=1), runs purely local. Same binary.
What you can build with it
- Persistent coding assistant that remembers your codebase, your decisions, your team's conventions
- Research agent that builds knowledge over time — Auto-Scholar pipeline ingests papers / docs and synthesizes
- Clinical scribe that retains patient context across visits (HIPAA-compliant cloud + local)
- Customer support agent that learns from every ticket
- Writing assistant that knows your voice, your prior drafts, and what you've already published
Companion: Prism Coder IDE
Standalone desktop AI IDE built on Prism's memory backend. macOS / Windows. Local-first 7B model handles routine edits; Standard+ tiers route to Claude Sonnet 4; Enterprise gets Claude Opus 4.
📚 Architecture, cognitive systems, and full feature catalog
Detailed docs in this repo:
docs/ARCHITECTURE.md— system architecture, memory routing, HRRdocs/SETUP_GEMINI.md— Gemini configurationdocs/self-improving-agent.md— adversarial eval / anti-sycophancydocs/rfcs/— design RFCsdocs/releases/— per-version release notesCHANGELOG.md— version history (v12.5 Unified Billing, v11.6 Hivemind, v11.5.1 Auto-Scholar, etc.)CONTRIBUTING.md— contributor guide
The original 1933-line README is preserved in git history. To browse the prior version (full feature catalog, Cognitive Architecture v7.8, Autonomous Cognitive OS v9.0, HRR Zero-Search, Adversarial Evaluation walkthroughs, Universal Import patterns, competitive analysis vs LangMem/MemGPT/Letta/Zep, v12.5 Unified Billing details, v11.6 Hivemind, v11.5.1 Auto-Scholar): git show HEAD~1:README.md.
License
BUSL-1.1 — Business Source License. Free for non-production use. Production use requires a Synalux subscription or commercial license. After 2 years, converts to MIT.
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found