Mex 0.8.0 – team memory for coding agents is a skill AI agent for Allow multiple AI coding agents to share context and historical decisions during collaboration to avoid redundant work. Pricing: not stated on the product page. As of 2026-09-25, KanonAgent records 2 upvotes. First indexed by KanonAgent on 2026-09-03.
Mex 0.8.0 provides a shared memory system for coding agents, enabling collaborative context retention across team members.
2 upvotes
Tracked by Kanon since Sep 3, 2026
Status basis: npm_downloads_7d momentum fell to -202 per 3d from 28 (<= 40% of the prior window)
📈 Timelinewhat changed, and when
- Cooling npm_downloads_7d momentum fell to -202 per 3d from 28 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -259 per 3d from 85 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -339 per 3d from 285 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 28 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -257 per 3d from 285 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 85 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 285 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 86 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 285 in the last 3d vs 86 in the 3d before (ratio 3.3x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 180 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 77 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 77 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 77 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change 94.0 is 5.8 standard deviations from this entity's own prior mean (-66.1±27.5, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change 94.0 is 5.8 standard deviations from this entity's own prior mean (-66.1±27.5, baseline excludes this point) — unusual, not necessarily adoption
- first observed Kanon started keeping permanent history for this agent
🔎 Known / Unknown
14 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | inferred | 1 quote(s) |
| Self-hostable | 1 | inferred | 1 quote(s) |
| Bring your own key | — | unknown | — |
| Autonomy level | — | unknown | — |
| Pricing model | — | unknown | — |
| Integrations | — | unknown | — |
“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 doneAllow multiple AI coding agents to share context and historical decisions during collaboration to avoid redundant work.
Who it is forAI programming teams and developers
Prerequisitesopen source · self-hostable
Why it matters
It addresses a core challenge in agent collaboration—context loss—making it a critical infrastructure component in the evolving AI agent ecosystem.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“npx mex-agent setup”— readme
“Every coding session starts with relevant architectural context instead of another full-repository scan.”— readme
“installs the official Claude Code and Codex skills”— readme
Signal source: Show HN
Visit official site →
📛 Official badgefor your site / README
Building Mex 0.8.0? 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 Mex 0.8.0?
Mex 0.8.0 provides a shared memory system for coding agents, enabling collaborative context retention across team members.
What does Mex 0.8.0 do?
Allow multiple AI coding agents to share context and historical decisions during collaboration to avoid redundant work.
Why does Mex 0.8.0 matter?
It addresses a core challenge in agent collaboration—context loss—making it a critical infrastructure component in the evolving AI agent ecosystem.
Is Mex 0.8.0 open source?
Yes — Mex 0.8.0 is open source.
Can I self-host Mex 0.8.0?
Yes — Mex 0.8.0 can be self-hosted.
How popular is Mex 0.8.0?
As tracked by KanonAgent: 2 upvotes (first indexed 2026-09-03).
What are the best Mex 0.8.0 alternatives?
Similar AI agents tracked by KanonAgent: open-design, Agent-Reach, deer-flow, ruflo, career-ops, archify.