Skip to content

The open-source benchmark for LLM memory decay. Measure how Naive, RAG, Chunked RAG, Cascading, and SummaryMemory degrade over 100 conversation turns. Ebbinghaus forgetting curves, 5-provider LLM eval, multi-seed CI. No API key needed.

active 2026-05-212026-07-04 (UTC)

Complete coverage26,758 / 26,758 hourly files (100%) · 2 absent upstream2023-08-152026-09-02 (UTC)
Events
51
Pushes
7
Pull requests
1
Issues
29
Stars
1
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 45 days from 2026-05-21 to 2026-07-04. Pushes: 7 total, peak 2 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 29 total, peak 25 in a day. Comments: 2 total, peak 2 in a day. Stars: 1 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
Neal00636700
Copilot3002
Priyanshu-byte-coder1010

Recent activity

Latest issues, pull requests and releases

  • Issue#29Neal0062026-05-24 06:15
    docs: Update README — new backends, scenarios, API server, HuggingFace Spaces badge
  • Issue#29Neal0062026-05-24 06:15
    docs: Update README — new backends, scenarios, API server, HuggingFace Spaces badge
  • Issue#29Neal0062026-05-24 06:15
    docs: Update README — new backends, scenarios, API server, HuggingFace Spaces badge
  • Issue#27Neal0062026-05-24 06:15
    feat: History tab — compare past benchmark runs side-by-side in the dashboard
  • Issue#27Neal0062026-05-24 06:15
    feat: History tab — compare past benchmark runs side-by-side in the dashboard
  • Issue#27Neal0062026-05-24 06:15
    feat: History tab — compare past benchmark runs side-by-side in the dashboard
  • Issue#27Neal0062026-05-24 06:15
    feat: History tab — compare past benchmark runs side-by-side in the dashboard
  • Issue#27Neal0062026-05-24 06:15
    feat: History tab — compare past benchmark runs side-by-side in the dashboard
  • Issue#27Neal0062026-05-24 06:15
    feat: History tab — compare past benchmark runs side-by-side in the dashboard
  • Issue#26Neal0062026-05-24 06:15
    feat: SQLite persistent storage — replace flat JSON logs with a queryable database
  • Issue#24Neal0062026-05-24 06:14
    feat: MedicalScenario — 8-fact patient-consultation domain benchmark
  • Issue#24Neal0062026-05-24 06:14
    feat: MedicalScenario — 8-fact patient-consultation domain benchmark
  • Issue#24Neal0062026-05-24 06:14
    feat: MedicalScenario — 8-fact patient-consultation domain benchmark
  • Issue#24Neal0062026-05-24 06:14
    feat: MedicalScenario — 8-fact patient-consultation domain benchmark
  • Issue#24Neal0062026-05-24 06:14
    feat: MedicalScenario — 8-fact patient-consultation domain benchmark
  • Issue#23Neal0062026-05-24 06:14
    feat: CustomerSupportScenario — 8-fact support-ticket domain benchmark
  • Issue#22Neal0062026-05-24 06:14
    feat: BaseScenario — abstract interface for all domain benchmark scenarios
  • Issue#22Neal0062026-05-24 06:14
    feat: BaseScenario — abstract interface for all domain benchmark scenarios
  • Issue#22Neal0062026-05-24 06:14
    feat: BaseScenario — abstract interface for all domain benchmark scenarios
  • Issue#22Neal0062026-05-24 06:14
    feat: BaseScenario — abstract interface for all domain benchmark scenarios
  • Issue#22Neal0062026-05-24 06:14
    feat: BaseScenario — abstract interface for all domain benchmark scenarios
  • Issue#22Neal0062026-05-24 06:14
    feat: BaseScenario — abstract interface for all domain benchmark scenarios
  • Issue#22Neal0062026-05-24 06:14
    feat: BaseScenario — abstract interface for all domain benchmark scenarios
  • Issue#21Neal0062026-05-24 06:14
    feat: contradiction_score — detect when context surfaces both old and new fact values
  • Issue#20Neal0062026-05-24 06:14
    feat: GraphMemory — knowledge-graph backend using NetworkX

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.