vectorize-io/hindsight
Hindsight: Agent Memory That Learns
About the project
Hindsight is a long-term memory system for AI agents that stores facts and observations rather than just conversation history, reporting state-of-the-art results on the LongMemEval benchmark. It runs as a server (Docker, pip, Helm) or embedded, with Python, Node.js, Go and CLI clients.
Useful for
- Attach Hindsight to an agent via the LLM wrapper or MCP so it retains facts across sessions
- Deploy the Hindsight server in Docker with a local ollama model for private agent memory
- Benchmark your own memory setup against Hindsight on LongMemEval
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 209 stars so far today, about 645 expected by the end of the day. The usual pace is 104 per day, so that's 6.2× as much.
- Over the last two days the pace is 7.7× that of the previous week and a half.
- The spike has held for 3 days in a row — not a one-off blip.
- GitHub Trending today: #2, +1,607 stars.
- GitHub Trending Python today: #2, +1,607 stars.
- About 141 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 26,934
- Today
- 209 · ≈ 645 by evening
- Forks
- 2,529
- Issues and pull requests
- 4,616
- Watchers
- 62
- Language
- Python
- License
- MIT
- Latest release
- v0.10.1 · September 21, 2026
- Created
- October 30, 2025
- Last push
- September 24, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 24, 2026GitHub Trending today: #2, +1,607 stars; GitHub Trending Python today: #2, +1,607 stars; GitHub Trending this week: #12, +3,181 stars
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/vectorize-io/hindsight)Similar by description
-
3.0
NxcoreAI/NxMem
A context and long-term memory engine for LLM agents: turns conversations and documents into structured facts, manages short- and long-term memory, and assembles cited context packs.
-
2.7
mem0ai/mem0
A long-term memory layer for AI agents and apps: stores user preferences, session state and facts so assistants keep context across conversations. Available as a Python/JS library, self-hosted server and cloud service.
-
0.6
Kerneta/daidocs
Open plain-text .dai format for AI assistant long-term memory: history lives as files on your disk, readable by any LLM and grep. Ships with an MCP server and hooks for Claude, Cursor, Windsurf, Codex.
-
2.0
supermemoryai/supermemory
Memory and context engine for AI: extracts facts from conversations, builds user profiles, combines RAG and memory in one API, runs locally or in the cloud.