Stele
Not yet source-checkedShared project memory for AI coding agents across Claude Code, Cursor, Codex, and Copilot
Machine-drafted from the vendor's site · not yet source-checkedProfile updated Link checked Pricing captured How we rate
In short
Stele provides shared project memory for AI coding agents like Claude Code and Cursor. It maintains a persistent graph of decisions and tasks to prevent context loss across tools and sessions.
Developers and small teams who juggle multiple AI coding agents (Claude Code, Cursor, Codex, Copilot) and want a persistent, shared project memory that survives tool switches and session resets.
Solo developers who stay inside one agent and one IDE, or enterprises with strict data-residency rules who cannot wait for the self-hosted edition.
Stele is a hosted shared-memory layer that lets multiple AI coding agents work on the same project without losing context between sessions or tools. It maintains a per-project graph of decisions, tasks, attempted-and-failed solutions, open risks, and lessons learned, which agents read before acting and update as they work. In practice, this means Claude Code, Cursor, Codex, GitHub Copilot, and any MCP-compatible client can pick up where another agent left off, avoid re-litigating design choices, and stop repeating the same failed refactors. Setup is a single-line CLI install that wires Stele into your MCP config; the platform then onboards itself by ingesting the existing codebase and building an initial project graph. A shared task queue lets agents (or humans directing them) claim work, hand off partial progress, and prevent two sessions from stepping on each other. The graph is self-maintaining: entries get flagged as stale when the code moves on, resolved risks retire themselves, and contradictions surface as conflicts rather than silently overwriting. Typical workflows include running one agent for architecture spikes and another for implementation, alternating between a laptop-based Cursor session and a cloud-based Codex run on the same ticket, or letting a Copilot-driven refactor consult the notes an earlier Claude Code session wrote about why a particular abstraction was rejected. Projects are private by default with export and deletion controls, and a self-hosted SQLite-backed edition has been announced for teams that need full data residency.
Stele is targeting a real pain point: agentic coding tools each have their own scratchpad, and switching between them today means re-explaining every architectural decision. Making the memory MCP-native instead of building yet another IDE plugin is the right call. Worth trying on the free tier if you actually rotate between Cursor, Claude Code, and Codex; less urgent if you have already picked one.
— The AI Tool Bible editorial team
Pros
- ✅ MCP-native, so it works with Claude Code, Cursor, Codex, and Copilot without per-tool adapters
- ✅ One-line CLI install with automatic onboarding from an existing repo
- ✅ Shared task queue prevents two agents from duplicating the same work
- ✅ Graph-based memory captures failed attempts, not just successful ones, so agents stop repeating dead ends
- ✅ Free tier is genuinely usable for solo developers (unlimited public projects, one private)
- ✅ Self-hosted SQLite edition on the roadmap for teams that need local data
- ✅ Export and deletion controls on private project graphs
Cons
- ⚠️ Currently hosted-only; the promised self-hosted build is not yet shipped
- ⚠️ Value depends on running multiple agents or switching tools often, less compelling for single-agent users
- ⚠️ Shared memory across agents can propagate a bad decision if not curated
- ⚠️ Early-stage product with limited public track record and small community
- ⚠️ Private project quota on the free tier is tight for anyone with several client repos
Pricing (captured )
| Tier | Monthly | Per seat | Key features |
|---|---|---|---|
| Free | $0 | — |
|
| Indie | $5.99 / month | — |
|
| Pro | $12 / month | — |
|
| Team | $20 / user / mo | Yes |
|
| Enterprise | — | — |
|
Prices change; we show the grid as captured on Oct 28, 2026. Check current pricing on the vendor's site →
Facts
- API available
- Yes
- Free trial
- Yes
- Hacker News
- 1 story · top 4 points · last Jul 22, 2026 · checked Oct 21, 2026
- Earliest Wayback capture
- 2026-07-22 (earliest archived capture of the site, not a launch date)
Where this tool sits
Use cases
Frequently asked
- How much does Stele cost?
- Stele uses a freemium model. The Free plan is $0 forever. Pro costs $12 per month, and the Team plan is $20 per user per month. These tiers support different levels of shared memory and collaboration needs.
- Which AI coding agents does Stele support?
- Stele integrates with Claude Code, Cursor, Codex, GitHub Copilot, and any MCP-compatible client. It acts as a shared memory layer, allowing these agents to read and update project context seamlessly across different tools.
- Is Stele difficult to set up?
- Setup is simple, requiring a single-line CLI install to wire Stele into your MCP config. The platform then automatically onboards by ingesting your existing codebase and building an initial project graph without manual configuration.
- Can I host Stele on my own servers?
- A self-hosted SQLite-backed edition has been announced for teams requiring full data residency. However, the current hosted version is the primary offering, and enterprises with strict rules may need to wait for this edition.
- How does Stele handle conflicting information?
- The project graph is self-maintaining. Entries are flagged as stale when code changes, resolved risks retire themselves, and contradictions surface as explicit conflicts rather than silently overwriting previous data.