tigerless-labs/agent-memory
Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.
3.6k stars · 158 forks · Python
Too new
Too new: created 43 days ago, so there is not enough history yet to judge.
Why
- Created 43 days ago, so there is not enough history yet to judge. (source 1)
What would change this
- The repository passes 60 days of age, and the verdict is computed on its full history.
Maintenance
CompleteActive
- Human commits, 30 days
- 80
- Human commits, 90 days
- 192
- Human commits, 365 days
- 192
- Bot share of commits, 365 days
- 0%
- Last commit
- Oct 14, 2026 (17 hours ago)
- Last human commit
- Oct 14, 2026 (17 hours ago)
- Authors, 90 days
- 10
- Last release
- none found
- Median PR merge time
- 17 hours
Responsiveness: of 5 recent issues, 40% got a maintainer reply. Median first response: 16 days.
Sources: Commits, Releases, Merged pull requests, Issues
People
Complete- Owner
- Organization
- Commits sampled
- 192 since Oct 15, 2025
- Authors for half of commits
- 1
- Authors for 80% of commits
- 2
- Contributors
- 9
Top committers
- liruihan000: 54% of commits
- faj-design5260: 36% of commits
- importcpp: 4% of commits
- ryan: 3% of commits
- dajiaohuang: 1% of commits
Sources: Commits, Contributors
Stars
CompleteNot enough data, confidence medium
Anyone can buy stars for any repo; bursts alone don't prove the owner did.
- Not enough star history yet to judge the star count.
Sources: How star history is analyzed
Risk
CompleteFlags
No risk flags.
License
- Now
- MIT (OSI-approved)
- A year ago
- Not known
Packages
No published packages found.
Sources: GitHub: tigerless-labs/agent-memory
Badge
Add this to a README to show the current verdict:
[](https://reporadar.ai/tigerless-labs/agent-memory)Earlier verdicts
- Oct 15, 2026: Too new
- Oct 14, 2026: Too new