Encodes conversation turns as hierarchically structured facts — world facts and experience facts consolidate into observations that merge into mental models, with automatic deduplication and evidence-tracking across updates. TEMPR retrieval runs four strategies in parallel (semantic, keyword/BM25, entity-graph, temporal) and merges results before returning them to the agent. Reflect reasons over retained memories using configurable mission, directives, and disposition settings per memory bank. Iris Extract provides a separate LLM-mediated structured-extraction pass for document ingestion. Memory banks are isolated namespaces; 40+ official framework adapters plus a first-party MCP server expose all operations.
- Storage
- Embedded Postgres backing four search indexes (semantic vector, BM25 keyword, entity-relationship graph, temporal store); deployed via Docker Compose, Helm chart, or pip/uvx. Hindsight Cloud provides a fully managed tier with daily backups, analytics dashboard, and 99.9% uptime SLA.
- Retrieval
- TEMPR: four strategies run in parallel — semantic similarity, keyword/BM25 for exact names and technical terms, entity-graph traversal for relationship queries, and temporal matching for time-anchored queries (e.g. 'last spring'); results merged and ranked before delivery. Mental Model Retrieve is a separate lower-cost path for high-level context.
- Self-host
- Self-host: moderate
- License
- MIT
- Pricing
- Self-host free, MIT licensed, no limits (Docker Compose / Helm / pip). Hindsight Cloud pay-as-you-go (repriced as of 2026-07-23): Retain $10.00/M tokens (was $15/M), Recall $0.75/M, Reflect $0.05/call (was $3/M — now billed per call, not per token), Iris Extract $7.50/M, Mental Model Retrieve $0.25/M, Mental Model Refresh $0.05/call (was $3/M — now per call), plus a new Storage line at $0.25/M tokens/month for memories held past their first 30 days (first 30 days free); free starter credits, no fixed monthly fee. Enterprise: custom pricing, dedicated infrastructure, up to 24x7 SLA, SSO and RBAC included. · Free + paid
- GitHub stars
- 19,457
- Last release
- 2026-08-07
- Last commit
- 2026-08-10
- First catalogued
- 2026-06-28
Strengths
- Strongest neutral benchmark scores on LongMemEval among catalogued frameworks
- TEMPR parallel retrieval combines semantic, BM25, entity-graph, and temporal search simultaneously for broad recall
- Reflect synthesis configurable via per-bank mission/directives/disposition — gives each agent a distinct memory personality
- 40+ official framework integrations (LangGraph, CrewAI, LlamaIndex, OpenAI Agents SDK, Zapier, Continue.dev, n8n, and more)
- Memory Defense security layer; OAuth 2.1 on Hindsight Cloud; audit logs, webhooks, and RBAC for enterprise use
Watch out
- Heavier self-host than append-only layers: four indexes (vector + BM25 + graph + temporal) running inside an embedded Postgres
- Cloud retain cost ($15/M tokens) can add up quickly at high write volume — benchmark your use case against the free self-hosted path first
- Remote MCP transport (remote-http via Hindsight Cloud) requires a cloud account; local deployment uses HTTP over localhost, not stdio
Best for
- Apps where recall accuracy is the priority (strong LongMemEval scores)
- Persistent memory for coding agents (Claude Code / Cursor / Continue.dev / OpenCode / Roo Code)
- Teams needing enterprise-grade memory: bank isolation, audit logs, webhooks, SSO, RBAC, and a managed cloud option
How it integrates
Benchmark results
| Benchmark | Value | Backbone | Trust | Source |
|---|---|---|---|---|
| beam-10m | 64.1 accuracy | — | Self-reported | Hindsight (Vectorize) ↗ |
| longmemeval | 91.4 accuracy | Gemini 3 Pro | Self-reported | Hindsight (Vectorize) ↗ |
Sources
- Billing rate card re-checked — unchanged, still the rates effective 2026-07-06: Retain $10.00/M input tokens, Recall $0.75/M output tokens, Reflect $0.05/call, Retrieve Model $0.25/M output tokens, Refresh Model $0.05/call, File Conversion (Iris) $7.50/M output tokens, Storage $0.25/M tokens/month (vendor)
- Monthly card re-verification — GitHub API repo metadata: 18,994 stars, license MIT confirmed, archived=false, last commit on the default branch 2026-07-31 (third-party)
- https://github.com/vectorize-io/hindsight (vendor)
- https://arxiv.org/html/2512.12818v1 (paper)
- Hindsight for persistent coding-agent memory (OpenCode / Claude Code / Cursor) (vendor)
- Official MCP server docs — HTTP transport, mounted at /mcp; OAuth 2.1 on cloud (vendor)
- Local MCP server — uvx launch command, exposes localhost:8888/mcp/ with embedded Postgres (vendor)
- REST API reference v0.8.3 — retain/recall/reflect, Iris Extract, banks, entities, mental models, webhooks, audit (vendor)
- Official Python SDK on PyPI — pip install hindsight-client; Python >= 3.10 (vendor)
- TypeScript/JS SDK docs — @vectorize-io/hindsight-client for Node.js and Deno (vendor)
- Hindsight Cloud pricing — Retain $15/M, Recall $0.75/M, Reflect $3/M, Iris Extract $7.50/M; free trial credits; Enterprise custom with dedicated infra (superseded 2026-07-23 repricing) (vendor)
- Hindsight Cloud pricing re-check — Retain now $10.00/M (down from $15/M), Reflect and Mental Model Refresh moved to $0.05/call (from $3/M), new Storage line $0.25/M tokens/month past a free 30-day window; Recall $0.75/M, Iris Extract $7.50/M, Mental Model Retrieve $0.25/M unchanged (vendor)
- GitHub API re-check — 18734 stars, MIT license confirmed, not archived, pushed 2026-07-23 (third-party)
- Hindsight docs homepage — TEMPR four-parallel-strategy retrieval; 40+ official integrations; Docker Compose / Helm / pip deployment options (vendor)
Last verified 2026-08-01 · updated by refresh-framework-cards