Evermind
Cross-session memory recovery for AI agents — your agent never cold-starts again. Always-loaded identity & todos, hash-indexed conditional reads cut recovery cost ~70% (~55-75% cumulative when the host already injects identity). Pure local, zero deps. Use when: (1) A new chat asks "where di
as observed 2026-09-14T16:18:15.105Z- Identifier
evermind-ai-agent-memory- Source
- ClawHub
- Version observed
- 0.4.4
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-09-05T08:21:05.203Z
- Observations recorded
- 5
- Installs (reported upstream)
- 1
- Weekly downloads (upstream)
- 436
Observation history
2026-09-14T16:18:15.105Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"0.4.3: publisher attribution corrected to TXJ; README cross-link to Mode Switch Kit. No behaviour change." | "0.4.4: paste-in instruction-file snippet (Hermes/OpenClaw/DeepSeek Harness) makes recovery run automatically; atomic index writes; config sample gains lang/output_dir." |
latestVersion |
"0.4.3" | "0.4.4" |
2026-09-12T14:17:54.398Z
Fields that differed: changelog description displayName latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"evermind-ai-agent-memory 0.4.1\n\n- Improved documentation and streamlined SKILL.md for clarity.\n- Removed deprecated skill-card.md.\n- Minor internal updates to scripts/memory_i | "0.4.3: publisher attribution corrected to TXJ; README cross-link to Mode Switch Kit. No behaviour change." |
description |
"The token-saving switch for AI agents. Kills long-context anxiety — start a new chat anytime, tasks pick up seamlessly, nothing breaks. Chat goes to zero. Progress is fully kept. | "Cross-session memory recovery for AI agents — your agent never cold-starts again.\nAlways-loaded identity & todos, hash-indexed conditional reads cut recovery cost ~70%\n(~55-75% |
displayName |
"evermind-ai-agent-memory" | "Evermind" |
latestVersion |
"0.4.1" | "0.4.3" |
summary |
"The token-saving switch for AI agents. Kills long-context anxiety — start a new chat anytime, tasks pick up seamlessly, nothing breaks. Chat goes to zero. Progress is fully kept. | "Cross-session memory recovery for AI agents — your agent never cold-starts again. Always-loaded identity & todos, hash-indexed conditional reads cut recovery cost ~70% (~55-75% cu |
2026-09-09T11:17:27.097Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"evermind-ai-agent-memory 0.4.0\n\n- Adds \"rule memory\": agent now restates all user-set rules at every session, and (where supported) enforces them via action hook—ending \"the | "evermind-ai-agent-memory 0.4.1\n\n- Improved documentation and streamlined SKILL.md for clarity.\n- Removed deprecated skill-card.md.\n- Minor internal updates to scripts/memory_i |
latestVersion |
"0.4.0" | "0.4.1" |
2026-09-08T10:18:19.295Z
Fields that differed: changelog description latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"0.3.0: zero-config discovery, semantic roles, context gauge, hardened yaml-less fallback, storefront copy" | "evermind-ai-agent-memory 0.4.0\n\n- Adds \"rule memory\": agent now restates all user-set rules at every session, and (where supported) enforces them via action hook—ending \"the |
description |
"The token-saving switch for AI agents. Kills long-context anxiety — start a new chat anytime, tasks pick up seamlessly, nothing breaks. Chat goes to zero. Progress is fully kept. | "The token-saving switch for AI agents. Kills long-context anxiety — start a new chat anytime, tasks pick up seamlessly, nothing breaks. Chat goes to zero. Progress is fully kept. |
latestVersion |
"0.3.0" | "0.4.0" |
summary |
"The token-saving switch for AI agents. Kills long-context anxiety — start a new chat anytime, tasks pick up seamlessly, nothing breaks. Chat goes to zero. Progress is fully kept. | "The token-saving switch for AI agents. Kills long-context anxiety — start a new chat anytime, tasks pick up seamlessly, nothing breaks. Chat goes to zero. Progress is fully kept. |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.