hindsight-api-slim
Hindsight: Agent Memory That Works Like Human Memory
Decision gist · record as of 2026-08-14
Yes, if you are building AI agents or LLM applications that require persistent, queryable memory with temporal and semantic reasoning. The low install friction, active maintenance, permissive license, and zero known vulnerabilities make it a solid choice. The substantial dependency footprint and requirement for Python 3.11+ and external LLM credentials are expected trade-offs for agent infrastructure. Not suitable if you need a lightweight memory layer or are working with Python versions below 3.11.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.11+.
- Async/await context required.
- Needs a PostgreSQL database (embedded by default, or external via HINDSIGHT_API_DATABASE_URL).
License · maintenance · safety
MIT (permissive) — MIT license is permissive; you can use, modify, and distribute this package freely in both open-source and commercial projects with minimal restrictions.
last release 2026-08-14 (0 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 80,552 downloads/mo, #14,286 on PyPI
Alternatives
Verify before relying
pip install hindsight-api-slim
from hindsight_api import MemoryEngine
memory = MemoryEngine()
await memory.initialize()
bank = await memory.create_memory_bank(name="agent", background="helpful assistant")
await memory.retain(memory_bank_id=bank.id, content="user prefers Python")
results = await memory.recall(memory_bank_id=bank.id, query="programming language preference?")- Whether the embedded PostgreSQL (pg0) is suitable for production workloads or intended only for development.
- Performance characteristics and scaling limits for memory recall with large fact stores.
- Whether the TEMPR retrieval strategy (semantic, keyword, graph, temporal with RRF fusion) is documented with benchmarks.
- Support status and breaking-change policy between 0.9.1 and future releases.
What it is and what it does
Hindsight-api-slim is a memory backend for AI agents that mimics human memory by storing facts, tracking entities and their relationships, and reasoning about time and context. It runs as a FastAPI server (default port 8888) backed by PostgreSQL with pgvector for semantic search, and exposes both a REST API and an MCP server interface for tool integration. The system supports three memory types (world facts, experience facts, and observations), combines multiple retrieval strategies (semantic, keyword, graph, and temporal), and allows agents to form opinions based on configurable disposition traits like skepticism and empathy.
The package is designed for AI agent frameworks and LLM applications that need persistent, queryable context across conversations. It integrates with multiple LLM providers (OpenAI, Anthropic, Gemini, Groq, Ollama, LMStudio) and includes Python SDK methods for creating memory banks, storing facts, recalling relevant memories, and reflecting on queries with reasoning. The dependency footprint is substantial—54 runtime packages including aiohttp, asyncpg, langchain-core, litellm, and observability tools—reflecting its role as infrastructure for complex agent systems.
Use it for
- Build a conversational AI assistant that remembers user preferences and past interactions across sessions without re-prompting.
- Create a multi-turn agent that tracks entities (people, projects, dates) and reasons about temporal relationships ("what happened last spring?").
- Implement a code review agent that learns from feedback, stores coding style preferences, and applies them to future reviews.
- Develop a customer support bot that maintains a knowledge graph of customer issues, resolutions, and patterns to improve future responses.
- Run an autonomous research agent that accumulates findings, tracks source relationships, and synthesizes insights over time.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building AI agents or LLM applications that require persistent, queryable memory with temporal and semantic reasoning.
The low install friction, active maintenance, permissive license, and zero known vulnerabilities make it a solid choice. The substantial dependency footprint and requirement for Python 3.11+ and external LLM credentials are expected trade-offs for agent infrastructure. Not suitable if you need a lightweight memory layer or are working with Python versions below 3.11.
Install
hindsight-api-slim on PyPI
Before you install
Low friction installation with a pure-Python wheel. Active maintenance as of 2026-08-14 with recent release. Requires Python 3.11 or later and brings in 54 runtime dependencies including LLM SDKs, async database drivers, and observability tools—a substantial dependency footprint typical of agent infrastructure.
Requires Python 3.11+. Async/await context required. Needs a PostgreSQL database (embedded by default, or external via HINDSIGHT_API_DATABASE_URL). Requires LLM API credentials (OpenAI, Anthropic, Gemini, Groq, Ollama, or LMStudio).
License in practice
MIT license is permissive; you can use, modify, and distribute this package freely in both open-source and commercial projects with minimal restrictions.
Quickstart
pip install hindsight-api-slim
from hindsight_api import MemoryEngine
memory = MemoryEngine()
await memory.initialize()
bank = await memory.create_memory_bank(name="agent", background="helpful assistant")
await memory.retain(memory_bank_id=bank.id, content="user prefers Python")
results = await memory.recall(memory_bank_id=bank.id, query="programming language preference?")Verify before relying
- Whether the embedded PostgreSQL (pg0) is suitable for production workloads or intended only for development.
- Performance characteristics and scaling limits for memory recall with large fact stores.
- Whether the TEMPR retrieval strategy (semantic, keyword, graph, temporal with RRF fusion) is documented with benchmarks.
- Support status and breaking-change policy between 0.9.1 and future releases.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.11 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 54 packagesaiohttpalembicanthropicasyncpgauthlibboto3claude-agent-sdkcoherecronitercryptographydateparserfastapifastmcpfilelockgoogle-authgoogle-genaigreenlethttpxjson-repairlangchain-corelangchain-text-splitterslangsmithlitellmmarkitdownobstoreopenaiopentelemetry-apiopentelemetry-exporter-otlp-proto-httpopentelemetry-exporter-prometheusopentelemetry-instrumentation-fastapi |
| Maintenance | Actively maintained 0 days since the last release |
| First released | |
| Downloads | 80,552 / month, #14,286 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: hindsight_api_slim-0.9.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “agent memory system”
- hindsight-api-slimHindsight-api-slim provides a persistent memory system for AI agents…
- echo-agentEcho Agent is a self-hosted, long-running AI agent runtime that…
- cogneeCognee builds a self-hosted knowledge graph from ingested data,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also agent-framework-mem0 · graphiti-core · hindsight-client · agent-framework-azure-ai · cognee · mem0ai · pydantic-ai-absurd · mindroom · memori · memsearch