Hindsight

Agent memory that learns from experience

Four retrieval strategies running in parallel. Token-budget optimization. Not RAG. Not a vector database wrapper. 94.6% on LongMemEval-S, peer-reviewed and independently reproducible.

View on GitHubTry Hindsight Cloud

Running agents at enterprise scale? Hindsight Enterprise →

New to agent memory? Start here →

Integration

Add memory in minutes, not sprints

No schema design. No manual tagging. No migration. Your agent starts building memory from the first conversation.

# pip install hindsight-client

from hindsight_client import Hindsight

client = Hindsight(base_url="http://localhost:8888")
client.retain(bank_id="my-bank", content="Alice prefers Slack over email")
results = client.recall(bank_id="my-bank", query="How does Alice communicate?")

Full REST API reference at hindsight.vectorize.io/api-reference. Frameworks, MCP servers and tools are in the Integrations Hub.

Stuck on integration? Ask in Slack.

Real engineers, real answers. The Hindsight team and community are one message away.

Join Slack

Under the hood

Four retrieval strategies. One query.

Dense vector search
Semantic similarity via embeddings
Finds conceptually related memories even when the wording differs.
Sparse vector search
BM25 keyword matching
Catches exact terms and proper nouns that semantic search misses.
Graph traversal
Entity relationship connections
Discovers linked context: person → project → preference.
Temporal search
Time-aware retrieval with causal chains
“What happened during onboarding last week?” with cause and effect.

All four run in parallel. Results merge with token budgets, not top-K. You get predictable context size, predictable cost, and the most relevant memories from four different angles.

Token budgets, not top-K
Token budgets control how much memory fits in your prompt (e.g., 4,096 tokens), unlike top-K which counts results (e.g., top 10) regardless of size. Predictable context window usage, predictable API costs.
Conflict detection
When facts change, both states are preserved with timestamps. “Alex used to prefer email, now prefers Slack” is more useful than silently overwriting.
Entity resolution
Batch disambiguation handles hundreds of entities in 3 database queries instead of hundreds. 99.5% query reduction.

State of the art. Peer-reviewed.

Retrieval accuracy on every benchmark with a published comparison: Hindsight against the next-best system on that dataset. The research is peer-reviewed and the benchmark code is open source.

Hindsight Next best system
LongMemEval-S
94.6%
74.0%
LoComo
92.0%
80.3%
PersonaMem
86.6%
84.4%
PrecisionMemBench
85.7%

no published comparison

LifeBench
71.5%
61.0%
BEAM · 10M tokens
64.1%
40.6%
Read the research All benchmarks

Open source, managed, or deployed for you

The same memory engine, API and MCP server, wherever your agents run.

MIT licensed

Open source

Hindsight 1.0 on Postgres, on your own infrastructure.

  • Runs with a single Docker command
  • No usage limits
  • No phone-home telemetry
View on GitHubRead the docs

SOC 2 Type 2

Hindsight Cloud

Managed Hindsight, pay-as-you-go on usage. You focus on your agent.

  • Infrastructure, scaling and upgrades handled
  • Daily backups
  • Same API and MCP interface as open source
Try Hindsight CloudSee pricing

Your cloud or ours

Hindsight Enterprise

A private cloud, your own AWS, Google Cloud or Azure account, or on premises.

  • Single-tenant isolation, SSO and Memory Defense
  • Hindsight Memlake for memory that grows into the billions
  • Contracted support in a shared Slack channel
Explore EnterpriseTalk to sales

Production ready

SOC2 Type 2 certified
Annual audit of security controls, availability, and data handling.
User isolation
Tag-based security boundaries prevent cross-user data leakage during memory consolidation.
No phone-home telemetry
Self-hosted Hindsight sends nothing back. Your data stays on your infrastructure.
Peer-reviewed research
Built on research from academic institutions. Results independently reproducible.

Start building agents that learn

Open source, MIT licensed. Self-host or use Hindsight Cloud.

View on GitHubTry Hindsight Cloud