memtrace-public is a skill AI agent for Provide AI coding agents with structured, zero-LLM-call memory storage for long-term context retention. Pricing: not stated on the product page. As of 2026-10-27, KanonAgent records 16 upvotes. First indexed by KanonAgent on 2026-07-10.
memtrace-public gives AI coding agents persistent, low-cost memory using a bi-temporal graph, eliminating the need for repeated LLM calls.
16 upvotes
Tracked by Kanon since Jul 10, 2026
Status basis: npm_downloads_7d gained 618 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
📈 Timelinewhat changed, and when
- Accelerating npm_downloads_7d gained 618 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 618 in the last 3d vs 36 in the 3d before (ratio 17.2x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 36 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 618 in the last 3d vs 36 in the 3d before (ratio 17.2x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 5 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 5 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -382 per 3d from 73 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -906 per 3d from 736 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -906 per 3d from 736 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -22 per 3d from 97 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -42 per 3d from 97 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -591 per 3d from 1068 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -1227 per 3d from 1704 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -1974 per 3d from 2354 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 1068 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -1286 per 3d from 2354 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 1704 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 2354 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 2354 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 503 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 503 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -2414 per 3d from 2802 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -2338 per 3d from 2802 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -2917 per 3d from 2802 (<= 40% of the prior window)
🔎 Known / Unknown
17 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | — | unknown | — |
| Bring your own key | — | unknown | — |
| Autonomy level | — | unknown | — |
| Pricing model | — | unknown | — |
| Integrations | cursor,claude-code,codex,hermes,vscode,w | inferred | 1 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
🤖 Agent teardown · skill
Job to be doneProvide AI coding agents with structured, zero-LLM-call memory storage for long-term context retention.
Prerequisitesopen source
Integrationscursor · claude-code · codex · hermes · vscode · windsurf
Why it matters
It solves the core scalability problem of AI agents by enabling efficient, durable memory without relying on expensive LLMs.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“AI coding agents can query in milliseconds”— readme
“across every session”— readme
“Cursor · Claude Code · Codex · Hermes · VS Code · Windsurf”— readme
Signal source: GitHub
Visit official site →
📛 Official badgefor your site / README
Building memtrace-public? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is memtrace-public?
memtrace-public gives AI coding agents persistent, low-cost memory using a bi-temporal graph, eliminating the need for repeated LLM calls.
What does memtrace-public do?
Provide AI coding agents with structured, zero-LLM-call memory storage for long-term context retention.
Why does memtrace-public matter?
It solves the core scalability problem of AI agents by enabling efficient, durable memory without relying on expensive LLMs.
Is memtrace-public open source?
Yes — memtrace-public is open source.
What does memtrace-public integrate with?
cursor,claude-code,codex,hermes,vscode,windsurf
How popular is memtrace-public?
As tracked by KanonAgent: 16 upvotes (first indexed 2026-07-10).
What are the best memtrace-public alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, taste-skill, archify, open-design, deer-flow, ruflo.