What Tablif read on Decispher Memory's site
Decispher Memory describes itself as: “Persistent Memory for AI Coding Agents | Decispher Decispher Products”
- Price model: free tier
- Free tier: Free forever
- Stage: Live, no waitlist
- How it differs: “A rules file is loaded in full on every session and shared by the whole team, so it drifts, competes for the model's instruction budget, and cannot hold anything personal. Decispher Memory selects the few memories relevant to what you are actually doing, keeps personal and team scopes separate, tracks whether a fact is still current, and writes a receipt every time something is served.”
What it is
Calls itself “Memory”.
- Calls itself: Memory
“Decispher Memory”
Where it puts itself
Rules out “A private memory never appears on an admin screen, a team view or another person's session.”. Publishes a comparison page.
- Says it will not: A private memory never appears on an admin screen, a team view or another person's session.
“A rules file is loaded in full on every session and shared by the whole team, so it drifts, competes for the model's instruction budget, and cannot hold anything personal. Decispher Memory selects the few memories relevant to what you are actually doing, keeps personal and team scopes separate, tracks whether a fact is still current, and writes a receipt every time something is served.”
“A private memory never appears on an admin screen, a team view or another person's session.”
What it costs
A free tier, free forever.
- Free plan: free forever
“Free to read · no credit card · delete anything, any time”
“Pricing -> https://decispher.com/pricing”
Who it sells to
Sells to businesses. Built for teams.
- Sells to: businesses
- Company size: teams
“Built for teams who care about why”
“Memory is a product you can adopt on its own, and plenty of teams should.”
How it runs
A command-line tool. Distributed through the npm. Offers an API. AI is the core of the product.
- Kind: cli
- Distributed via: npm
- API: yes
- AI role: core to the product
“Any agent that speaks the Model Context Protocol can request a memory by name.”
“…npx decispher init --only memory”
What it works with
Names Claude Code, Codex and 5 more on its pages.
- Names: Claude Code · Codex · Copilot · +4
“Claude Code”
“Codex”
What it offers as proof
Live, no waitlist. Claims “500 questions”. Try it without signing up. Publishes docs and a blog.
- Number claimed: 500 questions
- Instant signup: yes
- Trial asks for: nothing
“Sign up while seats are available”
“Free to read · no credit card · delete anything, any time”
Sources
Tablif read these pages, last on 13 Oct 2026. Everything above is what the product says about itself; Tablif does not verify every claim.
Similar products in Tablif Town
- Knowl: Persistent memory for AI coding agents
- Selvedge: Your coding agent's memory for decisions and dead ends
- Make0 Brain: A memory store that works across all of your AI agents.
- Singularity: Memory that makes your coding agent cheaper on repeat work
- ContextHarbor: Persistent project context for AI coding agents
- kadence: Shared memory for coding agents, kept in your git repo
- ResumeContext: Shared memory for coding agents.
- Hindsight 1.0 + Memlake: Open source memory for AI agents to learn from experience