All tags
Catalogue tag

#agent-memory

Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.

168 records
Tagged “agent-memory”Ranked by health index
npm
48Weakhealth index
sabaiway/agent-workflow
Portable, cross-agent memory & workflow for AI coding agents — Claude Code, Codex, Cursor, Devin, and more. Monorepo: memory substrate, the kit (composition root), CLI bridges, and the engine.
JavaScript★ 0↓ 11.5K/moSep 13, 2026
MITSep 13, 2026 · metrics 2.10.0
npm
47Weakhealth index
Alexander-Green/anchorClaw
OpenClaw Postgres-backed long-term memory plugin
TypeScript★ 0↓ 237/moSep 13, 2026
MITSep 13, 2026 · metrics 2.10.0
Go
47Weakhealth index
EclipseElips/recoil
Memory for AI coding agents — remembers what goes wrong, reminds you before it happens again. One Go binary, no embeddings.
Go★ 7Sep 9, 2026
MITSep 9, 2026 · metrics 2.10.0
npm
47Weakhealth index
ruvnet/agentdb
Vector memory that gets smarter every time your agent uses it.
TypeScript · HTML · JavaScript★ 89↓ 376.7K/moSep 13, 2026
MITSep 13, 2026 · metrics 2.10.0
Go
47Weakhealth index
valtors/vault
run your agent. it can't destroy your machine.
Go★ 1Sep 19, 2026
MITSep 19, 2026 · metrics 2.10.0
Go
45Weakhealth index
Dieg0Code/nem
Your agent forgets; nem doesn't. mnemonics encodes a session's decisions, edge-cases and facts into immutable, recallable structure — versioning agent context the way git versions code, shared across Claude & Codex.
Go★ 2Sep 10, 2026
MITSep 10, 2026 · metrics 2.10.0
PyPI · npm
45Weakhealth index
LycheeMem/LycheeMem
Lightweight Long-Term Memory for LLM Agents.
Python · TypeScript★ 1,079Sep 12, 2026
Apache-2.0Sep 12, 2026 · metrics 2.10.0
PyPI
44Weakhealth index
divyanshailani/graph-memory
Long-term graph memory skill using SQLite for coding agents like Antigravity AI , Claude & Codex.
Python★ 18↓ 587/moSep 18, 2026
MITSep 18, 2026 · metrics 2.10.0
Go
44Weakhealth index
mirkobrombin/go-lantern
Retrieval primitives for agent memory: embeddings, BM25, hybrid ranking
Go★ 0Oct 19, 2026
MITOct 19, 2026 · metrics 2.10.0
Go
42Weakhealth index
codysnider/tagmem
Structured local memory storage and retrieval for LLM agents
Go★ 15Sep 19, 2026
MITSep 19, 2026 · metrics 2.10.0
—
38Weakhealth index
AI4Outcomes/thinqos-plugins
Official AI4Outcomes plugin marketplace for Claude Code: thinqOS Mind integration
Shell · Python★ 0Sep 23, 2026
MITSep 23, 2026 · metrics 2.10.0
PyPI
34At Riskhealth index
Search2o/agent-server
Build hundreds of task-specific AI agents. Search runs the right agent for each request.
Python★ 0↓ 2,412/moOct 4, 2026
Custom licenseOct 4, 2026 · metrics 2.10.0
npm
33At Riskhealth index
ostinatocc/aionis-cli
Product CLI for installing and operating Aionis Runtime.
JavaScript · TypeScript★ 0↓ 9,374/moSep 7, 2026
No licenseSep 7, 2026 · metrics 2.10.0
—
30At Riskhealth index
Ghosts-Protocol-Pvt-Ltd/wyrm-mcp
Persistent memory for AI agents, over MCP. Local-first, negative learning, hybrid recall. Docs and community home (source is maintained privately).
Mixed★ 3Sep 16, 2026
Custom licenseSep 16, 2026 · metrics 2.10.0
PyPI
19Criticalhealth index
intertwine/observational-memory
Local-first shared memory for Claude Code, Codex, OpenCode, Kimi, Grok, Cowork, and Hermes, with bounded observation and searchable Markdown context.
Python★ 21↓ 375/moSep 11, 2026
MITSep 11, 2026 · metrics 2.10.0
npm
19Criticalhealth index
roackb2/heddle
An open-source terminal coding agent runtime and CLI for real project work.
TypeScript★ 25↓ 662/moSep 12, 2026
MITSep 12, 2026 · metrics 2.10.0
npm
19Criticalhealth index
shakystar/memorize
Shared, persistent memory for AI coding agents — Claude Code & Codex share one local-first, event-sourced project brain that survives sessions and syncs across machines. No server, no API key required.
TypeScript★ 14↓ 122/moSep 13, 2026
MITSep 13, 2026 · metrics 2.10.0
npm · Go
15Criticalhealth index
vshulcz/deja-vu
One memory shared by Claude Code, Codex, Cursor, Copilot CLI, OpenClaw and 20 more coding agents, built from the session history already on disk. A fix found in one agent comes back in any of them, including months of sessions from before you installed it. No LLM, no embeddings, one local Go binary.
Go★ 802↓ 5,667/moSep 12, 2026
MITSep 12, 2026 · metrics 2.10.0