Your AI team, working in Past.dev
Past.dev provides durable, source-backed memory for AI agents, including ingestion and its estimation and diagnostics, recall, identities, audiences, usage, request logs, memory traces, and explicit cleanup.
Start your companyWhat your team can do in Past.dev
29 tools to work with, connected with an API key.
Create or completely replace a fixed-list or trait-rule audience and its access definition. The default project audience cannot be replaced.
DESTRUCTIVE ACCESS CHANGE: Permanently delete an audience. Its stored memory remains but becomes permanently unreachable. The default project audience cannot be deleted.
DESTRUCTIVE: Permanently delete an identity directory record and remove it from every audience. Stored memory associated with the identity remains and is not deleted.
DESTRUCTIVE: Permanently delete one data point by its caller-owned source id and remove memory derived from it. This cannot be undone; the purge completes asynchronously.
DESTRUCTIVE: Permanently and atomically delete up to 1,000 data points by caller-owned source id and remove memory derived from them. This cannot be undone; the purge completes asynchronously.
Cut files into data points, plan batches, and estimate credits without storing data or spending credits.
Diagnose how far one send progressed, including per-item searchability, memory counts, failure details, and the recommended next step.
Find memory and source nodes for lineage or timeline inspection, returning independent memory and source cursors.
Read one API call and its retained allowlisted headers and request/response payload; bearer credentials are never returned.
Read one fixed, rule, or default audience with its definition and current membership and memory counts.
Return one identity's traits, origin, timestamps, and current audience memberships.
Poll one ingestion for processing, completion, failure, and project readiness without consuming metered request quota.
Count accepted, failed-later, and rejected API calls in provider-selected time buckets using request-log filters.
Read what a memory or source was built from and what was built on it, including graph edges and hidden-node count.
Read one memory or source node with revision, validity, replacement, request, content, and graph counts.
Read rooted source and memory work, ingestions, recalls, and supersessions on a clock for a window of at most 31 days.
Return the current UTC month's credit balance, metering state, and project ingestion, recall, and cap usage.
Ingest one timestamped data point into durable memory, optionally associating it with an identity and audience; reusing an id replaces the prior revision when stored fields change.
Atomically ingest 1 to 1,000 ordered memory data points in one request, avoiding fragile per-item agent loops.
List the connected project's API calls newest first, with filters and a cursor for the next page.
List every audience in the connected project, including the default project audience and current membership and memory counts.
List project identities newest first, optionally filtering by one trait, and return a cursor for the next page.
DESTRUCTIVE: Permanently delete every data point accepted by one ingestion and memory depending only on those points. This cannot be undone; the ingestion status and audit record remains readable.
Return ranked, source-backed memory visible to an identity for a query, with optional time range, sort order, and evidence budget controls.
Recompute an audience's membership from its definition and apply the refreshed access set to recall immediately.
Atomically create or replace complete trait sets for up to 1,000 identities; omitted traits replace the identity with no traits.
Create an identity or replace its complete trait set; omitted or empty traits remove all existing traits.
Retry a stopped or failed ingestion under its existing id without spending additional credits; completed ingestions are rejected.
Merge selected identity traits while preserving unspecified keys; set a trait value to null to remove that key.
Nothing matches that.
More in AI agents
See them all βCreate conversational voice agents using Bolna AI to enhance interactions, streamline operations and automate support.
97 toolsβ AAgent37 provides managed agent sandboxes, templates, networking, execution, scheduling, observability, budgets, and workspace administration throughβ¦
60 toolsβ AAnchor Browser is a developer platform that enables AI agents to interact with the web through browser automation, transforming complex webβ¦
64 toolsβ BBland AI is a conversational AI platform for building, operating, and evaluating voice agents, calls, messaging, and related communications workflows.
27 toolsβ BBlue Pillow provides AI agents with hotel and stay discovery, live offer comparison, recommendations, validation, and tracked booking handoff.
8 toolsβ CConductor is a cloud development platform for creating workspaces, running coding-agent sessions, exchanging messages, and searching sessionβ¦
17 toolsβ