Agent ADHD, meet graph memory
Side quests, forgotten context, and vibes where receipts should be. Continuity gives coding agents a hosted work graph: goal, evidence, blockers, and the next safe task.
Hosted CLI path
npm install -g @ligence/continuity
export CONTINUITY_API_TOKEN=<workspace-token>
continuity setup --json
continuity doctor --json
continuity next --agent codex --horizon overnight --compact --json
continuity agent-context --node task_42 --agent codex --json
continuity report-delta --node task_42 --kind completed --summary "verified" --jsonThe source-free npm package ships the CLI and docs only: no private repo, no local database, no native graph runtime.
The workspace token is the only required customer variable. Workspace identity resolves at the hosted API.
setup installs the agent contract. doctor checks API, package, skill, token, and graph readiness.
The graph returns the next work packet, then records completed work, failures, evidence, and judgment boundaries.
Orientation beats drift
An unguided agent drifts across competing signals until a human redirects it.
The agent starts from a prompt, follows several fading traces toward side quests and stale context, then needs a human redirect before reaching partial output.
prompt agent side quest stale thread unfiled debt partial output human redirectThe agent follows whatever signal is loudest. It can self-steer into side quests until a human re-enters the loop.
A work graph connects the active goal to tasks, decisions, evidence, debt, and the next action.
The graph starts with the active goal, branches into a decision and implementation task, reconciles evidence and debt, then selects the next runnable task.
Continuity gives every run provenance and direction: where it came from, what changed, and the next safe move.
Compaction survival
A compressed chat thread loses nuance as it becomes a short summary.
Signals for the reason, edge case, blocker, and next task converge into a compact summary while several important details fade away.
full thread why edge case blocker? next? short summaryCompaction keeps the headline, but the small reasons vanish: why the agent moved, what edge case mattered, and where the next run should resume.
A durable graph route survives compaction.
A routed path connects goal, decision, evidence, current task, and next task through a compaction gate without losing provenance or direction.
The graph is not just prose in the chat window. A future agent can inherit provenance, blockers, evidence, and next direction after the thread is compacted.
Why Linear and Jira are not enough
Human-updated status fields drift behind the actual work.
The graph is reconciled from runs, deltas, evidence, blockers, and decisions.
Important reasoning sits in comments, Slack, or a forgotten agent transcript.
Context is typed: goals, tasks, questions, branches, debt, and proof stay connected.
A human still decides what an agent should read, trust, ignore, and do next.
The graph selects the next agent-safe slice and explains why other work is blocked.
Receipts, stated precisely
Same model, same ten reconciliation tasks, hidden verifier reward. The operating protocol changed the outcome.
Clean runs. Failed the hidden custom fixtures.
Graph orientation, stop conditions, and reconciliation held across the same task family.
Useful pressure test. Not a matched Continuity comparison.
Claim boundary
Hard10 is a local Harbor-style suite, not a public benchmark. The same-model comparison is GPT-5.2 baseline versus GPT-5.2 with the Continuity protocol. A tiny two-instance SWE-bench Lite sample showed no score lift, so public benchmark proof remains ongoing.
The point is not that Continuity has finished proof. The point is that orientation changes terminal-agent behavior enough to justify serious first-customer trials, with artifacts and limitations visible.
Inspect the eval packet Read the trust protocolOutcome
The agent knows the outcome it is trying to create, not just the latest prompt.
Side quests become named future work instead of vanishing into chat history.
Each run records what changed, what was verified, and what still needs judgment.
The graph points the next agent at runnable work instead of another archaeology session.
trace exact work delta preserved
branch follow-up task created
exit clear next action
Pricing
Built for solo founders, founders, and small teams who love coding agents but are tired of supervising their memory.
Early access
For solo founders, founders, and small teams already using agents on production work and feeling the handoff tax.