Repository: vectorize-io/hindsight

Stars: 9456

CLAUDE.md Copy Chapter

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview Copy Chapter

Hindsight is an agent memory system that provides long-term memory for AI agents using biomimetic data structures. Memories are organized as:
- World facts: General knowledge ("The sky is blue")
- Experience facts: Personal experiences ("I visited Paris in 2023")
- Mental models: Consolidated knowledge synthesized from facts ("User prefers functional programming patterns")

Development Commands Copy Chapter

Local Development (API + UI) Copy Section

Start both API server and control plane UI

./scripts/dev/start.sh

API Server (Python/FastAPI) Copy Section

Start API server only (loads .env automatically)

./scripts/dev/start-api.sh
Run all tests (parallelized with pytest-xdist)

cd hindsight-api-slim && uv run pytest tests/
Run specific test file

cd hindsight-api-slim && uv run pytest tests/test_http_api_integration.py -v
Run single test function

cd hindsight-api-slim && uv run pytest tests/test_retain.py::test_retain_simple -v
Lint and format

cd hindsight-api-slim && uv run ruff check .
cd hindsight-api-slim && uv run ruff format .
Type checking (uses ty - extremely fast type checker from Astral)

cd hindsight-api-slim && uv run ty check hindsight_api/

Control Plane (Next.js) Copy Section

./scripts/dev/start-control-plane.sh
Or manually:

cd hindsight-control-plane && npm run dev

Documentation Site (Docusaurus) Copy Section

./scripts/dev/start-docs.sh

Generating Clients/OpenAPI Copy Section

Regenerate OpenAPI spec after API changes (REQUIRED after changing endpoints)

./scripts/generate-openapi.sh
Regenerate all client SDKs (Python, TypeScript, Rust)

./scripts/generate-clients.sh

Benchmarks Copy Section

Accuracy benchmarks

./scripts/benchmarks/run-longmemeval.sh
./scripts/benchmarks/run-locomo.sh
Performance benchmarks

./scripts/benchmarks/run-consolidation.sh
./scripts/benchmarks/run-retain-perf.sh --document <path>  # Requires API server running
Results viewer

./scripts/benchmarks/start-visualizer.sh  # View results at localhost:8001

Architecture Copy Chapter

Monorepo Structure Copy Section

Core Engine (hindsight-api-slim/hindsight_api/engine/) Copy Section

retain/: Memory ingestion pipeline
- orchestrator.py: Coordinates the retain flow
- fact_extraction.py: LLM-based fact extraction from content
- link_utils.py: Entity link creation and management

search/: Multi-strategy retrieval
- retrieval.py: Main retrieval orchestrator
- graph_retrieval.py: Graph retrieval abstract base class
- link_expansion_retrieval.py: Link expansion graph retrieval
- fusion.py: Reciprocal rank fusion for combining results
- reranking.py: Cross-encoder reranking

API Layer (hindsight-api-slim/hindsight_api/api/) Copy Section

Main operations:
- Retain: Store memories, extracts facts/entities/relationships
- Recall: Retrieve memories via 4 parallel strategies (semantic, BM25, graph, temporal) + reranking
- Reflect: Disposition-aware reasoning using memories and mental models.

Database Copy Section

Key tables: banks, memory_units, documents, entities, entity_links

Adding Database Migrations Copy Section

1. Create a new migration file in hindsight-api-slim/hindsight_api/alembic/versions/:
- File name format: <revision_id>_<description>.py (e.g., f1a2b3c4d5e6_add_new_index.py)
- Use a unique hex revision ID (12 chars)
- Set down_revision to the previous migration's revision ID

2. Migration template:

"""Description of the migration
   Revision ID: f1a2b3c4d5e6
   Revises: <previous_revision_id>
   Create Date: YYYY-MM-DD
   """
   from collections.abc import Sequence
   from alembic import context, op
   revision: str = "f1a2b3c4d5e6"
   down_revision: str | Sequence[str] | None = "<previous_revision_id>"
   branch_labels: str | Sequence[str] | None = None
   depends_on: str | Sequence[str] | None = None
   def _get_schema_prefix() -> str:
       """Get schema prefix for table names (required for multi-tenant support)."""
       schema = context.config.get_main_option("target_schema")
       return f'"{schema}".' if schema else ""
   def upgrade() -> None:
       schema = _get_schema_prefix()
       op.execute(f"CREATE INDEX ... ON {schema}table_name(...)")
   def downgrade() -> None:
       schema = _get_schema_prefix()
       op.execute(f"DROP INDEX IF EXISTS {schema}index_name")

3. Run migrations locally:

# Set database URL and run migrations for the base schema plus all tenants
   uv run hindsight-admin run-db-migration
   # Run on a specific tenant schema
   uv run hindsight-admin run-db-migration --schema tenant_xyz

Key Conventions Copy Chapter

Code Quality Copy Section

Before writing code, read .claude/skills/code-review/SKILL.md for the full coding standards (Python style, type safety, TypeScript style, general principles).

Always run the lint script after making Python or TypeScript/Node changes:

./scripts/hooks/lint.sh

After completing any implementation work, run /code-review to verify your changes against project standards (missing tests, dead code, type safety, etc.). Fix any "must fix" issues before considering the task done.

MANDATORY: Run /code-review before pushing code or creating a pull request. Do not push or create a PR until all "must fix" issues are resolved.

Memory Banks Copy Section

API Design Copy Section

Control Plane API Routes Copy Section

When adding or modifying parameters in the dataplane API (hindsight-api), you must also update the control plane routes that proxy to it:

1. API Routes (hindsight-control-plane/src/app/api/):
- recall/route.ts - proxies to /v1/default/banks/{bank_id}/memories/recall
- reflect/route.ts - proxies to /v1/default/banks/{bank_id}/reflect
- memories/retain/route.ts - proxies to /v1/default/banks/{bank_id}/memories/retain
- Other routes follow the same pattern

2. Client types (hindsight-control-plane/src/lib/api.ts):
- Update the TypeScript type definitions for recall(), reflect(), retain() etc.

3. Checklist when adding new API parameters:
- Add parameter extraction in the route handler (destructure from body)
- Pass the parameter to the SDK call
- Update the client type definition in lib/api.ts
- Update any UI components that need to use the new parameter

Adding New Integrations Copy Section

Every new integration in hindsight-integrations/ must satisfy all of the following before it can be merged:

1. Tests are required — tests must simulate or exercise the external system (mock the framework's interfaces and verify the integration actually calls Hindsight correctly). Pure unit tests of helper functions are not sufficient.
2. CI job — add a test job in .github/workflows/test.yml following the existing pattern (e.g., test-crewai-integration). The job must build, install deps, and run uv run pytest tests -v. Also add the integration to detect-changes outputs so it only runs when its files change.
3. Release process — add the integration name to the VALID_INTEGRATIONS array in scripts/release-integration.sh so it can be released via the standard release workflow.
4. Follow project code standards — Python style, type safety, no raw dicts for structured data, no multi-item tuple returns (see .claude/skills/code-review/SKILL.md).

If any of these are missing, the integration is incomplete and must not be pushed or merged.

Changelogs Copy Section

Never add "Unreleased" entries to changelogs (e.g. hindsight-docs/src/pages/changelog/). Changelog entries are written by the release script (./scripts/release-integration.sh) when a version is actually cut. If a bug fix or feature needs documenting before release, describe it in the PR/commit — the release tooling will surface it in the published changelog section.

Adding New API Configuration Flags Copy Section

Configuration follows a hierarchical system: Global (env vars) → Tenant (via extension) → Bank (database).

Fields must be categorized as either hierarchical (can be overridden per-tenant/bank) or static (server-level only).

#### Adding a New Configuration Field

1. config.py (hindsight-api-slim/hindsight_api/config.py):
- Add ENV_* constant for the environment variable name (e.g., ENV_MY_SETTING = "HINDSIGHT_API_MY_SETTING")
- Add DEFAULT_* constant for the default value
- Add field to HindsightConfig dataclass with type annotation
- Mark as configurable by adding to _CONFIGURABLE_FIELDS set if the field should be overridable per-tenant/bank via API
- Add initialization in from_env() method

# Configurable field (can be overridden per-tenant/bank via API)
   _CONFIGURABLE_FIELDS = {
       ...,
       "my_setting",  # Add here for configurable
   }
   # Static field - just don't add to _CONFIGURABLE_FIELDS

2. main.py (hindsight-api-slim/hindsight_api/main.py):
- Add field to the manual HindsightConfig() constructor call (search for "CLI override")

3. Use hierarchical config in MemoryEngine:

# Config is resolved automatically per bank via ConfigResolver
   config_dict = await self._config_resolver.get_bank_config(bank_id, context)
   value = config_dict["my_setting"]

4. Use static config (non-hierarchical):

from ...config import get_config
   config = get_config()
   value = config.my_static_field

5. Documentation (hindsight-docs/docs/developer/configuration.md):
- Add to appropriate section table with Variable, Description, Default
- Mark if it's hierarchical (can be overridden per-bank)

#### Hierarchical vs Static Guidelines

Hierarchical (per-bank overridable):
- LLM settings (provider, model, API key, base URL)
- Operation-specific settings (retain mode, chunk size, etc.)
- Feature flags that vary by customer/bank

Static (server-level only):
- Infrastructure settings (database URL, port, host)
- Global limits (max concurrent operations)
- System-wide feature flags

Environment Setup Copy Chapter

cp .env.example .env
Edit .env with LLM API key
Python deps

uv sync --directory hindsight-api-slim/
Node deps (uses npm workspaces)

npm install

Required env vars:
- HINDSIGHT_API_LLM_PROVIDER: openai, anthropic, gemini, groq, minimax, ollama, lmstudio
- HINDSIGHT_API_LLM_API_KEY: Your API key
- HINDSIGHT_API_LLM_MODEL: Model name (e.g., gpt-4o-mini, claude-sonnet-4-20250514)

Optional (uses local models by default):
- HINDSIGHT_API_EMBEDDINGS_PROVIDER: local (default) or tei
- HINDSIGHT_API_RERANKER_PROVIDER: local (default) or tei
- HINDSIGHT_API_DATABASE_URL: External PostgreSQL (uses embedded pg0 by default)
- HINDSIGHT_API_ENABLE_BANK_CONFIG_API: Enable per-bank config API (default: true)

README.md Copy Chapter

<div align="center">

!Hindsight Banner

Documentation • Paper • Cookbook • Hindsight Cloud

!PyPI - Downloads
!NPM Downloads
<br/>

<a href="https://trendshift.io/repositories/15603" target="_blank"><img src="https://trendshift.io/api/badge/repositories/15603" alt="vectorize-io%2Fhindsight | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
</div>

---

What is Hindsight? Copy Chapter

Hindsight™ is an agent memory system built to create smarter agents that learn over time. Most agent memory systems focus on recalling conversation history. Hindsight is focused on making agents that learn, not just remember.

<video src="https://github.com/user-attachments/assets/923b798d-3581-4897-bb62-9cfa5a931682" controls></video>

It eliminates the shortcomings of alternative techniques such as RAG and knowledge graph and delivers state-of-the-art performance on long term memory tasks.

Memory Performance & Accuracy Copy Chapter

Hindsight is the most accurate agent memory system ever tested according to benchmark performance. It has achieved state-of-the-art performance on the LongMemEval benchmark, widely used to assess memory system performance across a variety of conversational AI scenarios. The current reported performance of Hindsight and other agent memory solutions as of January 2026 is shown here:

!Overview

The benchmark performance data for Hindsight has been independently reproduced by research collaborators at the Virginia Tech Sanghani Center for Artificial Intelligence and Data Analytics and The Washington Post. Other scores are self-reported by software vendors.

Hindsight is being used in production at Fortune 500 enterprises and by a growing number of AI startups.

Adding Hindsight to Your AI Agents Copy Chapter

The easiest way to use Hindsight with an existing agent is with the LLM Wrapper. You can add memory to your agent with 2 lines of code. That will swap your current LLM client out with the Hindsight wrapper. After that, memories will be stored and retrieved automatically as you make LLM calls.

If you need more control over how and when your agent stores and recalls memories, there's also a simple API you can integrate with using the SDKs or directly via HTTP.

!Hindsight Banner

---

🤖 Using a coding agent? Install the Hindsight documentation skill for instant access to docs while you code:

``bash

`

export OPENAI_API_KEY=sk-xxx
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
  -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
  -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
  ghcr.io/vectorize-io/hindsight:latest

You can modify the LLM provider by setting HINDSIGHT_API_LLM_PROVIDER. Valid options are openai, anthropic, gemini, groq, ollama, lmstudio, and minimax. The documentation provides more details on supported models.

Docker (external PostgreSQL) Copy Section

export OPENAI_API_KEY=sk-xxx
export HINDSIGHT_DB_PASSWORD=choose-a-password
cd docker/docker-compose
docker compose up


>API: http://localhost:8888
>UI: http://localhost:9999

Client Copy Section

pip install hindsight-client -U
or

npm install @vectorize-io/hindsight-client

#### Python

from hindsight_client import Hindsight
client = Hindsight(base_url="http://localhost:8888")
Retain: Store information

client.retain(bank_id="my-bank", content="Alice works at Google as a software engineer")
Recall: Search memories

client.recall(bank_id="my-bank", query="What does Alice do?")
Reflect: Generate disposition-aware response

client.reflect(bank_id="my-bank", query="Tell me about Alice")

#### Node.js / TypeScript

npm install @vectorize-io/hindsight-client

const { HindsightClient } = require('@vectorize-io/hindsight-client');
const main = async () => {
  const client = new HindsightClient({ baseUrl: 'http://localhost:8888' });
  await client.retain('my-bank', 'Alice loves hiking in Yosemite');
  const results = await client.recall('my-bank', 'What does Alice like?');
  console.log(results);
}
main();

Python Embedded (no server required) Copy Section

pip install hindsight-all -U

import os
from hindsight import HindsightServer, HindsightClient
with HindsightServer(
    llm_provider="openai",
    llm_model="gpt-5-mini", 
    llm_api_key=os.environ["OPENAI_API_KEY"]
) as server:
    client = HindsightClient(base_url=server.url)
    client.retain(bank_id="my-bank", content="Alice works at Google")
    results = client.recall(bank_id="my-bank", query="Where does Alice work?")


---

Use Cases Copy Chapter


Hindsight is built to support conversational AI agents as well as agents that are intended to perform tasks autonomously. The ideal use case for Hindsight are agents that require a blend of these features such as AI employees that need to handle open-ended tasks, change behavior based on user feedback, and learn to perform complex tasks to automate work at a level that approximates a human work. Hindsight can be used with simple AI workflows like those built with n8n and other similar tools, but may be overkill for such applications.

Per-User Memories and Chat History Copy Section

One of the simpler use cases you can use Hindsight for is to personalize AI chatbots and other conversational agents by storing and recalling memories associated with individual users.

The requirements for this use case usually look something like this:

!Per-User Memories

<video src="https://github.com/user-attachments/assets/4805e8e1-e7d1-47c6-a4f8-2344a5ec8906" controls></video>

Satisfying these requirements in Hindsight is straightforward. When new user inputs and tool calls are ingested into Hindsight using the retain operation, custom metadata can be used to enrich the new memories. Metadata provides a convenient way to isolate memories that need to be restricted to a given user. Once these are fed into the retain operation, any raw memories and mental models that get created can be filtered when retrieving relevant memories.

!Per-User Memories

---

Architecture & Operations Copy Chapter

!Overview

Most agent memory implementations rely on basic vector search or sometimes use a knowledge graph. Hindsight uses biomimetic data structures to organize agent memories in a way that is more like how human memory works:

- World: Facts about the world ("The stove gets hot")
- Experiences: Agent's own experiences ("I touched the stove and it really hurt")
- Mental Models: Learned understanding of the agent's world formed by reflecting on raw memories and experiences.

Memories in Hindsight are stored in banks (i.e. memory banks). When memories are added to Hindsight, they are pushed into either the world facts or experiences memory pathway. They are then represented as a combination of entities, relationships, and time series with sparse/dense vector representations to aid in later recall.

Hindsight provides three simple methods to interact with the system:

- Retain: Provide information to Hindsight that you want it to remember
- Recall: Retrieve memories from Hindsight
- Reflect: Reflect on memories and experiences to generate new observations and insights from existing memories.

Retain Copy Section

The retain operation is used to push new memories into Hindsight. It tells Hindsight to _retain_ the information you pass in as an input.

from hindsight_client import Hindsight
client = Hindsight(base_url="http://localhost:8888")
Simple

client.retain(
    bank_id="my-bank",
    content="Alice works at Google as a software engineer"
)
With context and timestamp

client.retain(
    bank_id="my-bank",
    content="Alice got promoted to senior engineer",
    context="career update",
    timestamp="2025-06-15T10:00:00Z"
)

Behind the scenes, the retain operation uses an LLM to extract key facts, temporal data, entities, and relationships. It passes these through a normalization process to transform extracted data into canonical entities, time series, and search indexes along with metadata. These representations create the pathways for accurate memory retrieval in the recall and reflect operations.

!Retain Operation

Recall Copy Section

The recall operation is used to retrieve memories. These memories can come from any of the memory types (world, experiences, etc.)

from hindsight_client import Hindsight
client = Hindsight(base_url="http://localhost:8888")
Simple

client.recall(bank_id="my-bank", query="What does Alice do?")
Temporal

client.recall(bank_id="my-bank", query="What happened in June?")

Recall performs 4 retrieval strategies in parallel:
- Semantic: Vector similarity
- Keyword: BM25 exact matching
- Graph: Entity/temporal/causal links
- Temporal: Time range filtering

!Retain Operation

The individual results from the retrievals are merged, then ordered by relevance using reciprocal rank fusion and a cross-encoder reranking model.

The final output is trimmed as needed to fit within the token limit.

Reflect Copy Section

The reflect operation is used to perform a more thorough analysis of existing memories. This allows the agent to form new connections between memories and build a more thorough understanding of its world.

For example, the reflect operation can be used to support use cases such as:

- An AI Project Manager reflecting on what risks need to be mitigated on a project.
- A Sales Agent reflecting on why certain outreach messages have gotten responses while others haven't.
- A Support Agent reflecting on opportunities where customers have questions not answered by current product documentation.

The reflect` operation can also be used to handle on-demand question answering or analysis which require more deep thinking.

from hindsight_client import Hindsight
client = Hindsight(base_url="http://localhost:8888")
client.reflect(bank_id="my-bank", query="What should I know about Alice?")

!Retain Operation

---

Resources Copy Chapter

Documentation:
- https://hindsight.vectorize.io

Clients:
- Python
- Node.js
- REST API
- CLI

Community:
- Slack
- GitHub Issues

---

Star History Copy Chapter

---

Contributing Copy Chapter

See CONTRIBUTING.md.

License Copy Chapter

MIT — see LICENSE

---

Built by Vectorize.io

<img src="https://umami-pixel.chris-latimer.workers.dev/?id=a8b043e6-6964-454d-80df-69b69d3f0d50&host=github.com&url=/vectorize-io/hindsight" width="1" height="1" alt="" />