Stele
Stele is a hosted, invite-only shared memory (agentic ledger) for AI coding agents that provides a live project record of decisions, tasks, lessons and risks which every agent reads before acting and writes back to as it learns.
Stele is ai agents software teams evaluate for ai agents. Use this page to review pricing, integration signals, and the best alternatives before you commit.
Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.
Review official source →Used in These Packs
Quick Overview
Best for: AI Agents
What it does
AI Agents software for decision-makers comparing workflow fit and alternatives.
Best fit
AI Agents
Pricing snapshot
Contact for pricing
Next step
Compare Stele with similar tools before you shortlist it.
Compare this tool before you shortlist it
Review alternatives, pricing posture, and workflow fit side by side.
Stele
Stele is a hosted, invite-only shared memory for AI coding agents: a live project ledger that records decisions, tasks, lessons, risks and provenance. Every agent reads this project record before it acts and writes back what it learns, so the project context persists across tools and sessions. Stele is aimed at development teams and their agents: tasks belong to the project (not a person), agents claim work atomically to avoid duplicated effort, and the system surfaces prior decisions and risks during work to prevent repeated mistakes. The product is provided as a hosted service with a CLI installer and is currently invite-only beta.
Shared memory for AI coding agents — Claude Code, Cursor, Codex. Decisions, tasks, and lessons in one shared record.
Own this listing?
Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.
Claim this listing for $29Key Features
Shared project ledger (project memory)
A live record of decisions, tasks, lessons and risks that every agent reads before it acts and writes back to as it learns.
Atomic task claiming & coordination
Tasks belong to the project and are claimed atomically so two agents never start the same work; operators can read the open queue and hand off work between sessions.
Agent integrations / MCP compatibility
Plugs into common coding agents (e.g., Claude Code, Cursor, Codex) and any MCP-compatible client through the hosted server so multiple tools read/write the same graph.
Self-maintaining graph
Stale entries are flagged, resolved risks retire, duplicates surface, and agents re-verify facts against live code so the record remains trustworthy.
Provenance & traceability
Trace why anything exists by walking from a decision back to the task, document, risk and the person who made the call.
Built-in assistant
A project assistant answers from the live graph for status, history and where to start, with context already loaded.
Hosted service with CLI
Hosted product requiring no infrastructure to run; a one-line installer provides the stele CLI to sign in and seed a project record.
Privacy controls
Data is private per project, not sold or used to train models without consent; users can export or delete their project data.
Pricing
Current pricing details are not available from the vendor source.
Use Cases
Catch returning bugs
When a change risks reintroducing a past problem, the linked risk surfaces while work is happening so the agent can pause and ask instead of guessing.
Cross-agent continuity
Plan with one agent and build with another; multiple agents read and write the same graph so work continues when switching tools or sessions.
Team coordination & handoffs
Operators can pick up the open queue, run tasks end-to-end, and write handoffs so the next session resumes with full context.
Onboarding contributors
Point Stele at an existing repo to map code and docs into the record, making new human or agent contributors productive from day one.
Integrations
Claude Code
Reads and writes the shared project graph so it has project context.
Cursor
Integrates as a coding agent that shares the same project memory.
Codex
Works with the shared graph to maintain continuity across sessions.
Antigravity
Supported coding agent integration that reads/writes the project ledger.
Copilot / OpenCode
Coding agents that can read and write the project's shared memory.
Grok Build
Agent integration for reading and writing the project record.
Kimi Code CLI
CLI-based agent integration option.
Any MCP-compatible client
Supports any MCP-compatible client through the hosted server.
Benefits
Limitations
Frequently Asked Questions
What is Stele?
Which AI agents and tools does it work with?
How do I get access? Is it invite-only?
Can't I already do this with Notion, Obsidian, or a file in my repo?
Why pay when free, open-source graph and RAG tools exist?
Is my code and data private?
Do I have to run any infrastructure?
Getting Started
- 1 Step 1: Join the invite-only beta via the waitlist at stele-ai.dev and sign in with the invited email.
- 2 Step 2: Install the stele CLI (one-line installer shown on the site) and sign in with your invite email.
- 3 Step 3: Inside your agent, run /stele:start to let Stele wire into your project and build the initial record; then continue working as before.
Support
docs
Product documentation is available (see /docs) for usage and examples.
waitlist
Join the invite-only beta via the waitlist on the site to get access.
cli
Installation and sign-in are provided via the stele CLI installer referenced on the site.
site links
Footer links to Terms, Privacy, Security, Support and Licenses are available on the site.
API
https://stele-ai.dev/docs
Compare Stele with similar tools
See how it stacks up against alternatives
Related Tools
View all 512 →
Needle2
Needle 2 is an open, production-ready 45M-parameter agentic LLM from Cactus designed for tool calling, device control, and structured extraction on extremely small devices; the shipped CQ2-bit binary is ~14 MB and runs in ~28 MB of RAM across Cortex-M, microcontrollers, phones, Raspberry Pi and WebAssembly.
The cheapest GPU cloud
Compute Cheap provides low-cost GPU compute for training and inference, offering H100 and H200 SXM GPUs as interruptible or reserved capacity with published per-GPU-hour pricing and a simple request/reserve/run workflow.
Oodle.ai
Oodle Agent Observability provides agent/LLM observability at scale with S3-backed columnar storage, fast search (<1s P99), out-of-the-box AI-powered insights, and flat ingestion-based pricing designed to retain 100% of traces affordably for debugging and optimizing production agents.
Sentinel
Sentinel is an open-source (MIT) autonomous QA agent that reads a codebase to derive end-to-end business flows and tests them across frontend and backend, combining deterministic repo recon, model-driven planning, Playwright browser automation, and backend assertions.
Nous
Nous is an open-source context graph for agentic GTM (go-to-market) teams that centralizes identity-resolved people and company data from multiple GTM tools so agents can read a single, source-traced account context in one call. It is available as a hosted service and as a self-hostable stack.
Premium Alternatives
AletheionAGI
AletheionAGI provides a grounded-memory layer for AI systems that enforces evidence-bound delivery, namespace isolation, and policy authorization so AI readers cannot produce unsupported claims. It's targeted at production-facing use cases like customer support, commerce agents and internal copilots.
ClaudeThings
ClaudeThings provides a packaged, continuously-updating set of 89 specialized agents, 103 pre-built skills, and 181 slash commands that act as an AI engineering and marketing team for Claude Code — delivered as a private GitHub repo and installed with a single npx command. It adapts to any stack via a CLAUDE.md project manifest and is sold as a one-time purchase with lifetime updates.
ai-collective
AI Collective is a SaaS platform from Teknikforce that aggregates 50+ AI models (text and image) into a single multi-AI interface for content generation, image creation, coding, document Q&A and more, marketed to businesses and creators as a cost-saving alternative to multiple subscriptions.
lunarlink-ai
LunarLink is a beta web app that lets users access and compare multiple advanced AI models (including ChatGPT, Claude, and Gemini) side-by-side, with pay-as-you-go pricing matched to first-party API rates and a privacy-first chat experience.
Sitemanagerai
Site Manager AI is a web + iOS app that provides UK construction site managers and foremen instant, regulation-aware answers, on-site photo hazard analysis, and fast drafting of risk assessments, method statements and site reports.