Get This Tool
Genesys
Summary
You've told Claude you're training for a marathon. You've told ChatGPT the same thing. Tomorrow you'll tell the next tool, too — because every AI treats the last conversation like it never happened. Genesys is the memory layer that sits underneath all of them.
Genesys stores what you share in a causal graph you own, then surfaces that context to any app that speaks MCP — so Claude already knows what you told ChatGPT, without you repeating yourself. The graph explains its own reasoning: ask why it remembers something and you get the actual chain of connections, not a confidence score with nothing behind it. Memories fade by a scoring formula tied to relevance and reactivation, so stale data drops out without silently deleting things that still matter. The free tier caps writes at 300 stores per month — heavy users or teams running MCP agents hit that ceiling, then face a choice.
Bottom line: Genesys earns its place as the memory backbone for a solo developer or power user juggling ChatGPT and Claude daily — but teams building agents with high write volumes will hit the free cap fast and need to self-host or pay before they've shipped anything.
Hosted & API Pricing
The model is free to self-host. These are the creator's hosted/API options.Free
300 memory stores/month with full engine
- Scoring, causal graph, lifecycle
Founding Member
Locked forever for first 500
- Price locked while subscribed
Pricing may have changed since last verified. Check the official site for current plans.
Pricing Plans
Subscription- Price
- $0-$8/mo
- Free Tier
- 300 memory stores per month; recall remains unlimited
Free
300 memory stores per month with full engine features
- Full engine scoring and causal graph
- Unlimited reading and recall
Founding Member
Locked price for first 500 members
- Price locked for life while subscribed
- Full hosted service
View full pricing on genesys.astrixlabs.ai →
Pricing may have changed since last verified. Check the official site for current plans.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Cross-app memory over MCP, which means context you shared in ChatGPT appears in Claude without any manual sync — eliminating the re-introduction loop that breaks multi-tool workflows.
- Causal graph with inspect-and-correct capability, so when the memory layer gets something wrong you can trace why and fix it at the source rather than working around a black box.
- Evidence-based memory decay via a published scoring formula, which means stale context fades out without silently deleting nodes that are still connected and active — a common failure mode in simpler vector-store approaches.
- Open-source AGPL-3.0 engine with pip install and self-host support, so teams with data residency requirements or high write volumes can run their own backend instead of depending on the hosted service.
- Permanent, on-demand deletion with no retention games — the vendor states reading is never gated, so your memory graph does not go dark if you stop paying.
Cons
Sign in to edit- The free tier caps memory writes at 300 stores per month. An MCP agent that logs context on every turn hits this ceiling within a single moderately active project, forcing a choice between the paid hosted tier or standing up the self-hosted engine — which adds infrastructure overhead before you've validated anything.
- The graph is architected around a single personal memory, not a shared team workspace. Developers building multi-user products where agents need to carry context per-user at scale have no documented path to multi-tenant graph management — teams with that requirement will look at purpose-built agent memory backends like Mem0 or a custom vector store instead.
- MCP is the only integration protocol documented. Applications that do not speak MCP and cannot add a custom connector get no benefit from the graph — teams whose stack is locked to a non-MCP LLM API get nothing without building their own bridge.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Web, Python (pip)
- API Available
- Yes
- Self-Hosted
- Yes
- Last Updated
- 2026-07-22T08:16:03.899Z
Best For
Who it's for
- Users of multiple LLMs tired of re-explaining context
- Developers building MCP-native agents needing explainable memory
- Anyone wanting portable, deletable personal AI memory
What it does well
- Maintain consistent context across multiple AI chat apps
- Inspect and correct what AIs remember about the user
- Self-host agent memory with causal relationships and MCP tools
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Genesys free?
- Genesys has a permanent free tier alongside paid upgrades (paid plans from $0-$8/mo). You can keep using a baseline version indefinitely without paying.
- Is Genesys open source?
- Yes. Genesys is open source.
- Does Genesys have an API?
- Yes. Genesys exposes a developer API. See the official documentation at https://genesys.astrixlabs.ai for details.
- Can I self-host Genesys?
- Yes. Genesys supports self-hosting on your own infrastructure.
- What platforms does Genesys support?
- Genesys is available on: Web, Python (pip).
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Every AI chat application starts from zero. The context you built up over weeks in one tool sits trapped there while every other tool asks you to introduce yourself again. Genesys stores your personal context in a single graph and exposes it over MCP, so ChatGPT, Claude, and any MCP-native agent read from the same memory without manual re-entry. The core workflow: you share something once, Genesys stores it with a causal chain attached, and every connected app can recall and explain it on the next request.
The differentiating feature is explainability at the graph level. Most memory layers return a retrieved chunk and give you no visibility into why. Genesys lets you inspect every memory node, trace the causal relationships behind it, and issue corrections that propagate downstream — the vendor describes this as: one amendment updates everything connected to it. The scoring formula (relevance × connectivity × reactivation) governs what fades and what persists, and the vendor publishes both benchmark results and a failure ledger, claiming 85.55 on LoCoMo ahead of published alternatives under a documented protocol.
Genesys fits best as the personal memory layer for an individual moving across multiple LLM interfaces, or for a developer building an MCP-native agent who needs memory that is inspectable and deletable by design. It breaks down when write volume is high: the free tier allows 300 memory stores per month, and agents that log context aggressively will exhaust that before reaching any meaningful workload. Teams needing shared or multi-user memory graphs will also find the architecture oriented around a single personal graph — not a team workspace. At that point, self-hosting the open-source AGPL-3.0 engine via pip is the documented path forward, which means taking on infrastructure ownership.
Integration is MCP-native: Claude connects via a custom connector URL, and ChatGPT connects through a separate flow — both documented in the developer docs. The open-source engine is installable via pip as genesys-memory, supports MCP stdio, and allows running custom backends. Reading from the graph is never gated, including on the free tier — only writes are capped.