Status basis: github_stars momentum fell to 98 per 3d from 271 (<= 40% of the prior window)
- Cooling github_stars momentum fell to 98 per 3d from 271 (<= 40% of the prior window)
- Cooling github_stars momentum fell to 100 per 3d from 256 (<= 40% of the prior window)
- Anomaly daily change 32.0 is 3.4 standard deviations from this entity's own prior mean (19.1±3.9, baseline excludes this point) — unusual, not necessarily adoption
- Cooling github_stars momentum fell to 47 per 3d from 245 (<= 40% of the prior window)
- Anomaly daily change 47.0 is 13.3 standard deviations from this entity's own prior mean (18.2±2.2, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating github_stars gained 271 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Reactivated github_stars did not move for 7d, then gained 271 in the last 3d
- Anomaly daily change 10.0 is -3.8 standard deviations from this entity's own prior mean (18.1±2.1, baseline excludes this point) — unusual, not necessarily adoption
- Cooling github_stars momentum fell to 47 per 3d from 245 (<= 40% of the prior window)
- Accelerating github_stars gained 256 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Reactivated github_stars did not move for 7d, then gained 256 in the last 3d
- Anomaly daily change 11.0 is -7.8 standard deviations from this entity's own prior mean (18.8±0.0, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating github_stars gained 246 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Reactivated github_stars did not move for 7d, then gained 246 in the last 3d
- Anomaly daily change 11.0 is -7.8 standard deviations from this entity's own prior mean (18.8±0.0, baseline excludes this point) — unusual, not necessarily adoption
- first observed Kanon started keeping permanent history for this agent
| 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 | mcp,vscode,cursor | inferred | 1 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
Solves the core challenge of AI agents forgetting context, making it essential infrastructure for building advanced, multi-step AI workflows.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“A Go binary with SQLite + FTS5 full-text search, exposed via CLI, HTTP API, MCP server”— readme
“Persistent memory for AI coding agents”— description
“any agent that supports MCP — Claude Code, OpenCode, Gemini CLI, Codex, VS Code (Copilot), Antigravity, Cursor, Windsurf”— readme
FAQ
What is engram?
A persistent memory system that enables AI coding agents to store and retrieve information over time, supporting long-term context retention.
What does engram do?
Provide AI coding agents with long-term memory and retrieval capabilities to maintain context across sessions and tasks.
Why does engram matter?
Solves the core challenge of AI agents forgetting context, making it essential infrastructure for building advanced, multi-step AI workflows.
Is engram open source?
Yes — engram is open source.
Can I self-host engram?
Yes — engram can be self-hosted.
What does engram integrate with?
mcp,vscode,cursor
How popular is engram?
As tracked by KanonAgent: 43 upvotes (first indexed 2026-07-13).
What are the best engram alternatives?
Similar AI agents tracked by KanonAgent: open-design, deer-flow, Agent-Reach, ruflo, career-ops, orca.