The Landscape
Categories in the field this project maps. Entries are suppliers and reference points, not a ranking — most of them are solving a real, narrower problem than continuity, and the field needs all of them.
Memory systems
Infrastructure that stores and retrieves facts about a user, agent, or session across time — the supplier layer most continuity systems are built on top of.
Storing facts is the part of continuity that's closest to solved. Most of the field's visible activity — and funding — sits here, which makes it easy to mistake "has memory" for "has continuity."
Whether vendors start making project-level or decision-level claims (not just fact-recall claims) — that would be convergent-reinvention evidence, not a category collision.
Context engineering
Prompt- and retrieval-management techniques — long-context handling, RAG, retrieval pipelines — that decide what a model sees in a given call.
This is where most "my AI forgot" complaints actually get patched today: bigger windows, better retrieval. It extends what a single session can hold, which is adjacent to continuity but not the same claim.
The gap between advertised context length and usable context length (see RULER) — and whether retrieval-of-similar keeps getting sold as verification-of-current.
Stateful agents
Agent runtimes and frameworks that carry state across steps and tool calls within a task — distinct from raw memory storage and from multi-agent orchestration.
This is the layer that lets a single agent finish a multi-step job without re-deriving where it is. It's necessary for continuity but not sufficient — state-within-a-task isn't the same as understanding that survives a handoff to a different agent, tool, or person.
Whether framework-level state management starts getting described in project-continuity terms, or stays scoped to single-agent task execution.
Agent infrastructure
A real, active research field addressing attribution, identity, and interaction-shaping for AI agents — who acted, with what authority, leaving what trace.
It's the closest existing research to the questions this map tracks — who acted, with what authority, leaving what trace. An open question it raises but doesn't answer: what is accountability measured against? Audit trails need something to audit against, and whether that requires a project-level authoritative record is exactly the kind of underexplored question this map exists to track.
Whether this research extends toward project-level records, or continues to operate at the level of individual agent actions.
Provenance & audit
Work on tracing where a piece of AI-produced or AI-used information came from, and keeping an inspectable record of it.
Provenance is the evidentiary half of continuity: continuity says what changed and why; provenance says where the truth came from. Recent papers argue explicit provenance should be a requirement for responsible agentic systems, not an add-on.
Whether provenance tooling stays scoped to individual outputs (a single answer's sources) or extends to a project's whole decision history.
Long-running workflows
Orchestration and workflow systems built to survive interruption — checkpointing, retries, and resumption across long or multi-step processes.
Durable execution is a mature idea in distributed systems generally. Whether that maturity is being applied specifically to AI project continuity — versus just keeping a single long job alive — is an open, underexplored question this project is still mapping.
Whether any workflow-orchestration product starts explicitly framing its value in terms of preserved project understanding, not just preserved execution state.
MCP & tool continuity
Protocol-level efforts to move context and tool access between different AI hosts and surfaces.
If context can move between hosts, that's a plumbing precondition for continuity — but the protocol carries context, not judgment about what that context means or why it changed.
Whether MCP-adjacent tooling starts carrying decision lineage (not just tool schemas and context blobs) between hosts.
Personal AI memory
Consumer-facing tools that build a personal memory or persona from an individual's own activity, notes, or data.
This is the individual-scale mirror of project continuity: useful, real, and adjacent — but scoped to one person's recall, not to a project understood the same way by multiple humans and agents over time.
Whether personal-memory tools start being used as the substrate for multi-person or multi-agent project work, which would pull them toward project-level continuity.
Organizational memory
Pre-AI institutional-memory practices — wikis, decision logs, architecture decision records (ADRs), audit trails, commit lineage — that already solved fragments of this problem for decades.
AI didn't create the continuity problem; it multiplied it. Decades of partial answers here are the strongest evidence the underlying problem is real, and ADRs specifically are the direct structural ancestor of what this project generalizes into a living system.
Whether AI project tools start explicitly building on this lineage (citing ADRs, audit-trail practice) instead of treating memory as a green field.
Eval benchmarks
Papers and leaderboards that attempt to measure memory, long-context, or continuity-adjacent properties directly.
Benchmarks are how the field checks its own claims. Most existing benchmarks measure recall or long-context handling; very few attempt to measure continuity properties (update-handling, disambiguation, model independence) directly — that gap is itself informative.
Whether new benchmarks start testing update-handling and provenance together, rather than recall in isolation. See the Evidence Library for per-benchmark caveats and disputed results.
Open-source projects
Publicly inspectable code implementing memory, continuity, or agent-state tooling — as distinct from company-run or closed products.
Open code is rarer than it should be in this field, and it's the fastest way for independent parties to verify a claim rather than take a vendor's word for it.
Whether any of these projects attract independent contributors or replication attempts — single-maintainer repos are a different risk profile than actively co-maintained ones.
Papers
Academic and preprint research directly relevant to memory, continuity, provenance, or agent infrastructure.
Independent convergence across fields — ADRs in software, audit trails in accounting, provenance in science, "continuity of care" in medicine — is evidence the underlying abstraction is real, not invented for this project.
New papers that name the project-level gap explicitly, rather than working one layer down at the agent-action level. See the Evidence Library for the specific papers this project's own claims are built on.
Commercial
The business layer on top of memory, context, and agent-infrastructure technology — pricing, packaging, and go-to-market, as distinct from the underlying technique.
Watching what companies charge for (and what they bundle for free) is a signal of what the market currently believes is valuable — often narrower than what the research suggests is possible.
Whether any commercial memory product starts pricing or packaging around project-level continuity, rather than per-seat or per-token fact storage.
Unsolved problems
Open, question-framed territory this project tracks rather than claims to have answered.
A map that shows where the abstraction breaks is more credible than one where it always works. This category exists so the site doesn't quietly overclaim.
One underexplored question this project is tracking: whether long-running AI systems require project-level continuity in addition to agent-level infrastructure — and whether enough independent problems are converging that a category naturally wants to exist.
Where to go from the map
Entries above are reference points, not endorsements. From here: the live feed, then the receipts.