hindsight
What it does
An editorial selection.
Agent memory system built around agents that learn over time, not just recall chat history. Includes a paper and benchmarks.
Why it is listed
A research-backed alternative to plain RAG or knowledge-graph memory for long-running agents.
GitHub describes it as: Hindsight: Agent Memory That Learns
Counts were observed on 27/10/2026, 23:15:40 UTC. Observations older than 36 hours are excluded from current movement rankings.
Repository at a glance
- Stars
- 54,422
- Forks
- 6,291
- Open issues
- 163
- Merged PRs
- 3,351
- Commits, last 30 days
- 710
- Stars, 7 days
- unavailable
- Stars, 30 days
- unavailable
Counts observed on 27/10/2026, 23:15:40 UTC. Growth uses complete dated windows; see Methodology.
History
Project details
Explore and get started
Use the project's own documentation for supported platforms, dependencies and installation steps. The README and release notes are maintained by vectorize-io.
- Read the README and setup instructionsFeatures, prerequisites, examples and documentation links.
- Browse releases and changelogsPublished versions and the changes made between releases.
- Check licence and usage termsMIT is the licence reported by GitHub; read the repository terms before use.
- Read pull requestsProposed changes and development discussions.
- Browse reported issuesKnown problems, feature requests and maintainer responses.
Development context
These are observations of work in the repository. They do not establish quality, security or support commitments.
- Total commits on default branch
- 3,954
- Open pull requests
- 11
- Closed issues, lifetime
- 1,576
- Median time to close an issue
- 1.9 days
- Median time to merge a pull request
- 0.0 days
Close and merge times use up to 20 most recently updated closed issues or merged pull requests. They omit unresolved work and are context, not a maintenance score. Sample limits.
Explore the same category
Other projects in Context, Memory & Cost, ordered by shared topics and then name. These are discovery links, not equivalence claims.
- jonaslsaa/pi-optchat
Persistent infinite memory with profiles, background agents, and conversation imports for Pi.
- MemPalace/mempalace
Local-first AI memory with verbatim storage and pluggable backends. The README reports 96.6% R@5 on LongMemEval with zero API calls.
- MemTensor/MemT-1.0
Official repository for MemT-1.0
- 9bie/php2shell-bypass-aslr-exp
A php2shell exploit that requires no modifications to the official version, and does not require display_errors or limit_memory.
Found an incorrect description or number? Send a correction with this page's address and a source.