agentmemory is a skill AI agent for Providing AI coding agents with persistent memory to enhance context retention and long-term task execution. Pricing: not stated on the product page. As of 2026-10-27, KanonAgent records 45 upvotes. First indexed by KanonAgent on 2026-07-21.
agentmemory gives AI coding agents persistent memory based on real-world benchmarks, improving their ability to handle long-term tasks.
45 upvotes
Tracked by Kanon since Jul 21, 2026
Status basis: npm_downloads_7d momentum fell to -349 per 3d from 869 (<= 40% of the prior window)
📈 Timelinewhat changed, and when
- Cooling npm_downloads_7d momentum fell to -349 per 3d from 869 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -349 per 3d from 869 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -349 per 3d from 869 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -10682 per 3d from 635 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -10682 per 3d from 1075 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 1835 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 635 per 3d from 5501 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 1075 per 3d from 5061 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 1835 per 3d from 8968 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 1200 per 3d from 8968 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 8968 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change 4301.0 is 8.2 standard deviations from this entity's own prior mean (71.4±514.0, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change 4301.0 is 8.2 standard deviations from this entity's own prior mean (71.4±514.0, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 8968 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 4667 in the last 3d vs 55 in the 3d before (ratio 84.9x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 4667 in the last 3d vs 55 in the 3d before (ratio 84.9x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to -46 per 3d from 52 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -46 per 3d from 52 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -125 per 3d from 61 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -125 per 3d from 61 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -82 per 3d from 170 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 61 per 3d from 990 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -70 per 3d from 2016 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 170 per 3d from 1737 (<= 40% of the prior window)
🔎 Known / Unknown
15 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | 1 | inferred | 1 quote(s) |
| Bring your own key | — | unknown | — |
| Autonomy level | — | unknown | — |
| Pricing model | — | unknown | — |
| Integrations | claude-code,github-copilot-cli,cursor,ge | 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 doneProviding AI coding agents with persistent memory to enhance context retention and long-term task execution
Prerequisitesopen source · self-hostable
Integrationsclaude-code · github-copilot-cli · cursor · gemini-cli · codex-cli · mcp
Why it matters
By grounding memory in real-world performance data, it solves the core issue of AI agents forgetting context during extended development tasks.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“Persistent memory for Claude Code, GitHub Copilot CLI, Cursor”— readme
“Persistent memory for AI coding agents”— description
“Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Codex CLI, ... and any MCP client.”— readme
Signal source: GitHub
Visit official site →
📛 Official badgefor your site / README
Building agentmemory? 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 agentmemory?
agentmemory gives AI coding agents persistent memory based on real-world benchmarks, improving their ability to handle long-term tasks.
What does agentmemory do?
Providing AI coding agents with persistent memory to enhance context retention and long-term task execution
Why does agentmemory matter?
By grounding memory in real-world performance data, it solves the core issue of AI agents forgetting context during extended development tasks.
Is agentmemory open source?
Yes — agentmemory is open source.
Can I self-host agentmemory?
Yes — agentmemory can be self-hosted.
What does agentmemory integrate with?
claude-code,github-copilot-cli,cursor,gemini-cli,codex-cli,mcp
How popular is agentmemory?
As tracked by KanonAgent: 45 upvotes (first indexed 2026-07-21).
What are the best agentmemory alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, ECC, orca, Agent-Reach, taste-skill, archify.