# vectorize-io/hindsight

Hindsight: Agent Memory That  Learns

Repository: https://github.com/vectorize-io/hindsight
Canonical: https://ross.abutalabs.com/products/hindsight
Homepage: https://hindsight.vectorize.io/
Language: Python
License: MIT
License Family: permissive
Topics: agentic-ai, memory, agents, ai-memory
Last push: 2026-08-26T19:09:13+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 21
- inputs: {"age_days": 307, "days_push": 7, "days_rel": 8, "gap_med": 2, "n_releases_24m": 68}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 21228, forks 1638 (observed 2026-08-28T04:11:31.445960+00:00)

## What it is
Hindsight is an open-source agent memory system that gives AI agents persistent long-term memory that learns and consolidates knowledge over time, using facts, observations, mental models, and graph-based relationships instead of raw RAG chunks. It runs as a self-hostable API server (Python, backed by PostgreSQL) with clients in Python, TypeScript, Go, and CLI, plus an MCP server and dozens of integrations with agent frameworks and coding agents.

## Use cases
- add persistent long-term memory to my AI agent
- make my chatbot remember users between sessions
- give Claude Code or Cursor memory of my project's decisions
- replace RAG with a memory system that does temporal reasoning
- store and recall user preferences across conversations
- add memory to LangGraph or Vercel AI SDK agents
- self-host an agent memory server with MCP support

## When to choose
- you need agents that remember and consolidate knowledge across sessions, not just retrieve documents
- you want state-of-the-art long-term memory accuracy (LongMemEval) with temporal and graph reasoning
- you need per-user or per-project memory banks with multi-tenant isolation
- you want a self-hostable, PostgreSQL-backed memory service with broad framework integrations
- you want coding agents to learn project conventions from git history and past sessions

## When to avoid
- you only need simple vector search over static documents - plain RAG or a vector database is simpler
- you need a fully managed zero-ops solution and don't want to run a server or use Hindsight Cloud
- your agent is stateless by design and memory would add unwanted latency or complexity
- you require an LLM provider without structured output support, which Hindsight depends on

## Facets
- artifact type: service
- maturity: active
- function: rag, vector-database, agent-framework, mcp, llm-inference, api-framework, search-engine
- domain: artificial-intelligence, large-language-models, developer-tools, self-hosted
- platform: python, self-hosted, cross-platform, go, cli
- tags: agent-memory, long-term-memory, memory-banks, temporal-reasoning, knowledge-graph, mental-models, coding-agents, langgraph, vercel-ai-sdk, mcp-server, postgresql, ai-agents, retrieval-augmented-generation, docker, nodejs

## Member repositories
- vectorize-io/hindsight (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:31.445960+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:58:27.903673+00:00, confidence not recorded.
  - readme: https://github.com/vectorize-io/hindsight (fetched 2026-08-28T04:11:31.445960+00:00, sha d40ec80a0225)
  - homepage: https://hindsight.vectorize.io/ (fetched 2026-08-29T07:57:03.537390+00:00, sha b9c039478d14)
  - site_page: https://hindsight.vectorize.io/developer/api/quickstart (fetched 2026-08-29T07:57:03.549500+00:00, sha 70a025fcc7ae)
  - site_page: https://hindsight.vectorize.io/integrations (fetched 2026-08-29T07:57:03.540501+00:00, sha 376424cd843f)
  - site_page: https://hindsight.vectorize.io/changelog (fetched 2026-08-29T07:57:03.542649+00:00, sha 2c315f8e32d5)
  - site_page: https://hindsight.vectorize.io/faq (fetched 2026-08-29T07:57:03.547003+00:00, sha 4bd74ef94ce1)
  - site_page: https://hindsight.vectorize.io/sdks/integrations/coding-agents (fetched 2026-08-29T07:57:03.551496+00:00, sha 556268647158)
  - site_page: https://hindsight.vectorize.io/sdks/integrations/langgraph (fetched 2026-08-29T07:57:03.554292+00:00, sha 6b99ba4574cb)
  - site_page: https://hindsight.vectorize.io/sdks/integrations/ai-sdk (fetched 2026-08-29T07:57:03.556222+00:00, sha 8c72061af7b2)
  - site_page: https://hindsight.vectorize.io/sdks/integrations/chat (fetched 2026-08-29T07:57:03.557956+00:00, sha 7994e2aca45f)
- Data as of 2026-08-30T08:39:29.467469+00:00.