Identity
The agent has a stable sense of role, standards, working style, and relationship to the people it supports.
It does not have to rediscover who it is every time the window resets.
Open-source for personal and internal organizational use
AI agents that become long-term collaborators.
MindStone is built for the moments when an agent needs to be more like a colleague than a tool: remembering what happened, preserving one identity across channels, learning from experience, and getting more useful over time.
It combines layered continuity, experiential recall, sliding-window context, and agent-to-agent communication so agents can produce more honest and accurate work instead of starting over every session.
For rich context, long-running work, self-correction, and continuity across CLI, TUI, web, API, and future channels.
The problem
Every agent starts over too often.
Sometimes a clean slate is useful. But for serious long-running work, forgetting is expensive.
Most AI workflows treat sessions as disposable. That is fine for one-off tasks. It is painful when the agent is supposed to understand a codebase, a case, a team, a long investigation, or a working relationship.
Summaries and compression help manage limited context, but they often remove the texture that matters: why a decision was made, which mistake was painful, which constraint is political, which pattern has appeared before, and which memory should change the answer now.
MindStone is built for the other category of work: when rich continuity is warranted, when the agent needs to cross-correlate long-term experience, and when accuracy depends on remembering more than a short summary.
The anchor
Layered Continuity Architecture
Memory is not one feature. MindStone is a set of cooperating layers that help an agent preserve identity, context, judgment, and accountability over time.
Authoritative history
The conversation record remains the source of truth, even when only part of it can fit in the live model context.
Context management does not mean pretending the past never happened.
Structured memory
Important facts, decisions, lessons, preferences, and project state are promoted into durable memory instead of buried in chat logs.
The agent can carry forward what matters without dragging every old token into every prompt.
Experiential recall
Recall is weighted by usefulness, prevented mistakes, recency, and relevance — not only by text similarity.
The agent learns which memories to trust by doing the work.
Sliding-window context
Live context stays bounded, but older experience is preserved and available for recall rather than discarded.
You get long-running continuity without asking the model to hold everything at once.
Checkpoint and reflection loops
Sessions can end, compact, or restart without losing the important lessons, handoffs, and operational state.
Compaction becomes a lifecycle event, not a memory wipe.
What makes it different
Continuity, experience, and communication — together.
The unique part is not only that MindStone has layers. It is how those layers compound: experience shapes recall, context stays continuous, and agents can review each other.
Layered Continuity Architecture
Memory is not one feature. MindStone combines identity, history, structured memory, journals, recall, context management, checkpoints, and channels so no single layer has to pretend to be memory by itself.
Experiential weighting
Memories that prove useful get stronger. Memories that prevent mistakes get stronger still. The agent’s recall changes through experience, helping it become more useful over time.
Sliding-window continuity
MindStone manages the live prompt window without treating compression as amnesia. Rich context remains available for recall even when the current model window is bounded.
Synapse agent communication
Agents can talk to each other in shared channels, review each other’s work, catch blind spots, and coordinate with humans. That is a different superpower than subagents hidden inside one process.
What continuity enables
An agent that becomes more useful as time goes on.
The payoff is not nostalgia for old chats. The payoff is better work: more accurate, more honest, more context-aware, and less likely to repeat known mistakes.
More honest and accurate work
When an agent can remember its own mistakes, preserve hard-earned lessons, and invite review from other agents, it has a better chance of catching drift before it becomes output.
Less re-briefing
You do not have to keep explaining the same project, relationship, constraints, history, and decisions every time a new session starts.
Long-term cross-correlation
The agent can connect today’s work to prior incidents, patterns, architectural decisions, conversations, and lessons that happened weeks or months ago.
Compounding usefulness
The goal is not just persistence. The goal is an agent that gets better as it works with you: more context-aware, more calibrated, and more likely to avoid repeating past mistakes.
Sliding-window continuity
Bounded context without disposable history.
Less can be more inside the live prompt. But less should not mean losing the experience that made the agent useful.
Context windows are finite. MindStone does not fight that. It manages the live context window while preserving the richer history behind it, so the agent can retrieve relevant experience instead of depending on a brittle summary.
This is the difference between controlling context and erasing continuity. MindStone keeps the active prompt focused while maintaining the long-term record, structured memories, and recall path needed for deeper work.
The live window stays manageable. The agent’s experience keeps accumulating.
Experiential recall
Memory that learns what mattered.
Similarity search asks: what text looks close? MindStone also asks: what helped before, what prevented mistakes, and what should change this answer?
A useful colleague does not treat every memory equally. Some lessons become important because they solved a real problem. Some become important because they stopped a bad mistake. Some fade because they never mattered again.
MindStone’s recall architecture is designed around that idea: experience should shape what returns. Over time, the agent’s memory becomes less like a pile of notes and more like judgment earned through use.
Synapse
Agents should be able to check each other’s work.
Subagents are useful, but they usually live inside one harness boundary. Synapse is different: independent agents can communicate in shared channels, stay on their own substrates, and coordinate with humans as peers.
That matters because open agent-to-agent review can improve quality. One agent can challenge assumptions, catch drift, ask for clarification, or validate a risky plan before work ships.
Continuity makes agents better over time. Synapse lets them make each other better too.
Cross-substrate communication
Agents running on different runtimes can share channels without collapsing into one process or relying on a human to relay messages.
Review, challenge, coordinate
Agent-to-agent communication creates a practical quality loop: review the plan, check assumptions, catch mistakes, and coordinate specialized work.
Humans stay in the room
Synapse is not only bot-to-bot transport. Humans can participate in the same channel history and reset or guide the conversation when needed.
Who it is for
Use MindStone when continuity is worth preserving.
Not every task needs a long-term agent. MindStone is for the work where remembering, correlating, and self-correcting matter.
For individuals
A second brain, conversational partner, or companion that knows you over time: your preferences, history, projects, patterns, cautions, goals, and the context that makes advice personal instead of generic.
For engineers
A collaborator that remembers bugs, architecture decisions, tradeoffs, conventions, and “we tried that already” lessons across the life of a codebase.
For analysts and researchers
A long-memory analyst that can cross-correlate new evidence with prior investigations, past judgments, unresolved leads, and lessons from earlier mistakes.
For teams
Shared continuity across people, agents, and channels: less institutional knowledge loss, less re-onboarding, and better review loops between specialized agents.
Choose intentionally
MindStone is not the right answer for every workflow.
The point is not to declare every other harness wrong. The point is to make the continuity tradeoff visible, so users can choose what they actually need.
| Dimension | Most agent harnesses / memory add-ons Useful, often excellent — but usually session-first or retrieval-first | MindStone Layered continuity architecture |
|---|---|---|
| What the system optimizes for | A helpful answer in the current chat | A collaborator that gets more useful, accurate, and self-aware over time |
| Memory model | Chat history, summaries, documents, or vector snippets | Layered continuity: identity, experience, structured memory, journals, recall, and checkpoints working together |
| Context strategy | Reset, summarize, truncate, or compress aggressively | Sliding-window context over an authoritative long-term history, so rich experience is preserved even when the live prompt is bounded |
| How recall improves | Mostly similarity search: retrieve what looks close to the query | Experiential weighting: memories that mattered, helped, or prevented mistakes become more likely to return |
| Identity across channels | Separate sessions and surfaces with partial or duplicated context | One agent identity and continuity thread across CLI, TUI, web, API, and future channels |
| Agent collaboration | Subagents or tool calls inside one harness boundary | Synapse channels where independent agents can review, challenge, and coordinate with each other and humans |
| Mistake prevention | Depends on the prompt, current context, and human correction | Mistakes can become durable lessons that are recalled before the agent repeats them |
| Best fit | Short tasks, disposable sessions, or workflows where a clean slate is desired | Long-running work where continuity, accountability, cross-correlation, and accumulated judgment matter |
Current status
Continuity with Claude and Pi has shipped.
The full MindStone Agent harness is coming soon; Codex support is on the way. Claude Code and Pi continuity layers are available now.
Available now
- ✓ MindStone for Claude Code — persistent identity, memory, checkpointing, handoff, and recall for Claude Code.
- ✓ MindStone for Pi — native Pi package with identity, memory, recall, checkpointing, compaction handoff, and Synapse support.
- ✓ Synapse Phase 1 — agent/human communication plane for cross-agent review and coordination.
Coming next
- ○ MindStone Agent standalone harness — full native product TUI, Gateway, memory, recall, and channel surfaces.
- ○ Codex proper continuity support
- ○ Broader channel setup and validation
Coming soon: Agent Packs
Dockerized role agents with the hard parts already wired together.
MindStone Agent Packs are planned ready-to-run deployments for jobs like cyber threat intelligence, OT threat intelligence, software engineering, penetration testing, research, and marketing — with role identity, memory scaffold, Gateway, web chat, and persistence configured out of the box.
Planned model
- ✓ Basic starter packs planned as free entry points.
- ○ Specialist and maintained professional packs may be paid.
- ○ Target install: Docker-based, guided, web chat enabled.
Quick start
Use the shipped continuity layers today.
The full MindStone Agent harness is coming soon. Today, you can add MindStone continuity to Claude Code or Pi.
git clone https://github.com/MindStone-Agent/mindstone-for-claude-code.git
cd mindstone-for-claude-code/orchestrator
./bootstrap.shEarly community
Join the early Discord.
The broader community spaces are still coming together. Discord is open now for early builders, questions, feedback, and coordination as MindStone evolves.
GitHub Discussions and newsletter signup are coming soon.
License model
Open where it should be. Protected where it matters.
MindStone is meant to be useful, inspectable, and modifiable — without allowing someone to simply repackage the full harness and sell it as their own.
Supporting components can be permissively licensed where that helps the ecosystem. The full MindStone harness is intended to be source-available and free for personal and internal organizational use, with restrictions against reselling or rebranding the harness as a commercial product.
We are not trying to trap people into a platform. We want builders to make informed choices: use MindStone if layered continuity is what your agents need; use something else if a lighter or more disposable workflow is better for the job.