hindsight vs Supermemory
Two of the top projects in Memory, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
hindsight
Agent memory server with retain, recall and reflect operations
Supermemory
Memory and context engine for AI agents, with user profiles and hybrid search
Verdict
hindsight ranks higher, 95 to 89. Of the 4 score parts we measure for both, hindsight leads on 2, Supermemory on none and 2 are even.
- Adoptionhindsight leads by 16 points, 95 to 79: a wide gap.
- FreshnessEven at 100.
- MaintenanceEven at 94.
- Agent-readyhindsight leads by 15 points, 85 to 70: a wide gap.
Pick hindsight if you are
Developers adding persistent memory to agents or coding assistants
- Four parallel retrieval strategies (semantic, BM25, graph, temporal) with cross-encoder reranking
- Works with 25+ LLM providers, including local ones: ollama, lmstudio, llamacpp
Pick Supermemory if you are
Developers adding long-term memory to agents, apps and AI coding tools
- Hybrid search returns RAG documents and user memories in a single query
- Handles knowledge updates and contradictions, and auto-forgets expired facts
| What we compare | hindsight | Supermemory |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 95, widely used | 79, popular |
| Freshness | 100, active | 100, active |
| Maintenance | 94, healthy | 94, healthy |
| Agent-ready | 85, ready | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 60.6k | 31.6k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Nov 2026 | Oct 2026 |
| Language | Python | TypeScript |
| Docker | Yes | No |
| GPU | Not stated | Optional |
| arm64 or Apple Silicon | Mentioned | Mentioned |
hindsight
Hindsight is a long-term memory system for agents. It uses an LLM to extract facts, entities and time data on retain, then recalls them with semantic, BM25, graph and temporal search, merged by reciprocal rank fusion and a cross-encoder rerank. It also consolidates facts into observations and mental models, and ships Python, TypeScript and Go clients, a CLI and a per-bank MCP endpoint.
Who it is for: Developers adding persistent memory to agents or coding assistants
Strengths
- Four parallel retrieval strategies (semantic, BM25, graph, temporal) with cross-encoder reranking
- Works with 25+ LLM providers, including local ones: ollama, lmstudio, llamacpp
- Python, Node.js and Go clients, CLI, REST API and a built-in MCP endpoint per bank
- Embedded pg0 database by default; external PostgreSQL and Helm chart also supported
Weaknesses
- Retain depends on an LLM call for fact extraction, adding provider cost and latency
- Dashboard, backups and uptime SLA are described only for the hosted Hindsight Cloud
- Benchmark claims are partly vendor-reported; only some were independently reproduced
- Intel Macs need the hindsight-all-slim package instead of the default
- Docker
- Needs LLM provider (API or local), PostgreSQL (embedded pg0 by default)
- Models: openai, anthropic, gemini, groq, bedrock
- port 9999
Supermemory
Supermemory extracts facts from conversations, tracks updates and contradictions, expires stale information, and returns a per-user profile plus relevant memories through one API. It also covers RAG, connectors (Google Drive, Gmail, Notion, OneDrive, GitHub) and file extraction. It can be used via the hosted API, an MCP server and editor plugins, or a local server on port 6767.
Who it is for: Developers adding long-term memory to agents, apps and AI coding tools
Strengths
- Hybrid search returns RAG documents and user memories in a single query
- Handles knowledge updates and contradictions, and auto-forgets expired facts
- Local server keeps data in ~/.supermemory and can use Ollama with local embeddings
- Plugins for Claude Code, Cursor, Codex, OpenCode, plus Vercel AI SDK, LangChain, Mastra wrappers
Weaknesses
- Benchmark #1 claims are self-reported in the README, with details on a separate research page
- Hosted MCP server and plugins point at supermemory.ai cloud by default
- Local mode URL ingestion depends on a hosted reader service
- Local-versus-Enterprise feature differences are only documented on a separate page
- GPU optional
- Needs LLM provider (OpenAI, Anthropic, Gemini, Groq, or Ollama), Docker (optional)
- Models: OpenAI, Anthropic, Gemini, Groq, Ollama
- port 6767
More in Memory
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.