🔥 26,900+ GitHub Stars · Trending Globally · v3.0.0 Released

The Highest-Scoring
AI Memory System.
Free. Local. Forever.

MemPalace stores every AI conversation verbatim, then makes them instantly findable. 96.6% on LongMemEval with zero API calls — beating every paid competitor. Built by Milla Jovovich & Ben Sigman using Claude Code.

pip install mempalace
0%
LongMemEval Raw
0%
Hybrid Mode Score
$0
Forever Free
0
GitHub Stars
19
MCP Tools
Advertisement · 728×90

Your AI Has Amnesia. MemPalace Fixes That.

Decisions happen in conversations now — not in docs, not in Jira. In conversations with Claude, ChatGPT, Copilot. Six months of daily AI use equals 19.5 million tokens of reasoning, decisions, and breakthroughs. All trapped in chat windows that evaporate when the session ends.

ApproachTokens LoadedAnnual Cost
Paste everything into context19.5M — doesn't fitImpossible
LLM summarization tools~650K tokens~$507/yr
⭐ MemPalace wake-up (L0+L1)~170 tokens~$0.70/yr
⭐ MemPalace + 5 searches~13,500 tokens~$10/yr

Store Everything. Find Anything.

Unlike Mem0 and Zep — which use an LLM to decide what's "worth remembering" and discard the rest — MemPalace stores your actual exchanges in ChromaDB without summarization or extraction. The 96.6% LongMemEval result comes from this raw verbatim mode.

🏛️

The Palace Structure

Inspired by the ancient method of loci used by Greek orators. Your conversations are organized into Wings (people/projects), Rooms (topics), Halls (memory types), Closets (summaries), and Drawers (verbatim originals).

🗄️

Raw Verbatim Storage

Every conversation stored in ChromaDB exactly as written — no LLM deciding what to throw away. Semantic vector search retrieves the right memory in milliseconds. This is what drives the benchmark-topping 96.6% score.

🔗

Halls & Tunnels

Halls connect rooms within the same wing by memory type: facts, events, discoveries, preferences, advice. Tunnels cross-reference the same topic across different wings automatically.

4-Layer Memory Stack

L0 (identity, ~50 tokens), L1 (critical facts, ~120 tokens), L2 (room recall, on demand), L3 (deep semantic search, on demand). Your AI wakes up with 170 tokens and knows your entire world.

🧠

Knowledge Graph

Temporal entity-relationship triples stored in SQLite — free alternative to Zep's Graphiti (Neo4j). Track who decided what, when, and why. Invalidate outdated facts. Query any point in the past.

🤖

Specialist Agents

Create agents that focus on specific domains — code reviewer, architect, ops. Each gets its own wing and AAAK-compressed diary. Scale to 50+ agents with zero CLAUDE.md bloat. Replaces Letta ($20–200/mo) at zero cost.

Navigate Your Memory

  ┌─────────────────────────────────────────────────────────────┐
  │  WING: wing_kai  (Person)                                   │
  │                                                            │
  │    ┌──────────────┐  ─hall─  ┌──────────────┐             │
  │    │ hall_facts   │          │ hall_events  │             │
  │    └──────┬───────┘          └──────────────┘             │
  │           │  room: auth-migration                         │
  │           ▼                                               │
  │    ┌──────────┐      ┌─────────────────────────────┐      │
  │    │  Closet  │─────▶│  Drawer (verbatim original) │      │
  │    └──────────┘      └─────────────────────────────┘      │
  └───────────┼─────────────────────────────────────────────────┘tunnel  (same room topic, different wing)
             │
  ┌───────────┼─────────────────────────────────────────────────┐
  │  WING: wing_driftwood  (Project)                            │
  │           │  room: auth-migration                         │
  │    ┌──────┴───────┐  ─hall─  ┌──────────────┐             │
  │    │ hall_facts   │          │hall_discoveries│            │
  │    └──────┬───────┘          └──────────────┘             │
  │           ▼                                               │
  │    ┌──────────┐      ┌─────────────────────────────┐      │
  │    │  Closet  │─────▶│  Drawer (verbatim original) │      │
  │    └──────────┘      └─────────────────────────────┘      │
  └─────────────────────────────────────────────────────────────┘

  Halls: hall_facts · hall_events · hall_discoveries · hall_preferences · hall_advice
  Search impact:  All closets: 60.9% R@10  →  Wing+Room filtered: 94.8% R@10  (+34%)

Best Score. Zero Cost.

MemPalace raw mode (zero API, zero cost) outperforms every paid competitor on the industry-standard LongMemEval benchmark.

SystemLongMemEval R@5API RequiredMonthly CostLocal
⭐ MemPalace hybrid (Haiku rerank)100%OptionalFree
⭐ MemPalace raw (zero API)96.6%NoneFree
Supermemory ASMR~99%YesPaid
Mastra94.87%Yes (GPT)API costs
Mem0~85%Yes$19–249/mo
Zep~85%Yes$25/mo+

Running in Under 60 Seconds

bash
# Install
pip install mempalace

# Initialise your palace (guided, detects people & projects)
mempalace init ~/projects/myapp

# Mine your conversations (Claude, ChatGPT, Slack exports)
mempalace mine ~/chats/ --mode convos

# Search six months of context in milliseconds
mempalace search "why did we switch to GraphQL"
→ "Chose GraphQL over REST — concurrent writes, dataset exceeds 10GB. 2025-11-03"

What People Are Saying

"We tested MemPalace at The Zero-Human Company and deployed it to 79 employees. This is a masterpiece."

Brian Roemmele — AI Industry KOL

"Milla Jovovich launching an AI memory system was NOT on my 2026 bingo card."

Wayne Sutton — 1.2M+ impressions

"Milla Jovovich has a GitHub. She co-developed the highest-scoring AI memory system. What a boss."

@am_will — Twitter community

"Yes, that Milla Jovovich. Missed opportunity to call it Resident Eval." — top HackerNews comment, denysvitali

HackerNews — Top comment on launch day
0
GitHub Stars
0
Forks
0
Watchers
0
Contributors
0
Commits