agent memory plugins

260 tagged agent memory, measured the same way as everything else here.

Browse within: ai-memory 46local-first 18context-engineering 17knowledge-management 14coding-agents 13knowledge-graph 13knowledge-base 10openclaw 9RAG 6agentskills 6bm25 6coding-agent 6golang 6plugin-marketplace 6

memesh

97

PCIRCLE-AI/memesh

Plugin Claude Code

MeMesh — agentic memory for coding agents. Captured from the agent's real work via hooks, recalled when it acts. One SQLite file, zero cloud required.

15 yesterday A tokens not measured original MIT

vukkt-plugins

98

vukkt/token-warden

Plugin Claude Code

Plugins by Vuk Topalovic — currently token-warden, a measurement and selection layer that makes Claude Code subagents measurably cheaper over time.

13 4d ago A tokens not measured original MIT

token-warden

99

vukkt/token-warden

Plugin Claude Code

Agent memory, charged rent. A Stop hook records what each session costs; expensive runs are distilled into candidate efficiency rules; each candidate is benchmarked on a frozen golden suite and kept only if it saves at least twice its context rent. Six commands. Two theorems survived measurement and three were deleted.

13 4d ago A tokens not measured original MIT

local-agent-toolkit

101

jnMetaCode/local-agent-toolkit

Plugin Claude Code

Local-first memory, skills and tracing for your agent: engram (recall/remember your notes via MCP), skillet (search/install agent skills via MCP), plus skills that teach the agent to use them — nothing leaves your machine.

12 2mo ago A tokens not measured

kernel-marketplace

102

ariaxhan/kernel-claude

Plugin Claude Code

Safety guardrails, cross-host hooks, and agentdb memory for Claude Code and Codex in auto mode.

12 2d ago A tokens not measured original MIT

kernel

103

ariaxhan/kernel-claude

Plugin Claude Code

KERNEL is a Claude Code and Codex plugin that replaces per-action approval prompts with guardrails enforced by hooks. Hook context is shaped for both hosts' plain and structured output parsers. In auto mode, destructive commands and secret writes are blocked before they run; irreversible operations require a one-time…

12 2d ago A tokens not measured original MIT

rembric

104

susomejias/rembric

Plugin Claude Code

Plugin marketplace listing 1 plugin: rembric.

12 7d ago A tokens not measured original MIT

rembric

105

susomejias/rembric

Plugin Claude Code

Memory for Claude Code, backed by your self-hosted Rembric server.

12 7d ago A tokens not measured original MIT

titen

106

RamaAditya49/titen

Plugin Claude Code

Evidence-grounded collaborative memory for coding agents.

11 2d ago A tokens not measured original Apache-2.0

titen-memory

107

RamaAditya49/titen

Plugin Claude Code

Use Titen's evidence-grounded collaborative memory. The local stdio mode needs no configuration; a served Titen endpoint is the alternative for a shared store.

11 2d ago A tokens not measured original Apache-2.0

squish-memory

108

michielhdoteth/squish-memory

Plugin Claude Code

Persistent memory system for Claude Code via Squish CLI - remembers conversations, injects context, auto-captures tool results.

11 5d ago A tokens not measured original MIT

exomem

109

Artexis10/exomem

Plugin Claude Code

Plugin marketplace listing 1 plugin: exomem.

10 2d ago A tokens not measured AGPL-3.0

exomem

110

Artexis10/exomem

Plugin Claude Code

Governed long-term memory over a markdown vault: raw sources stay immutable, conclusions are compiled with provenance, and nothing is deleted - it is superseded. Requires EXOMEMVAULTPATH to point at your vault; run exomem setup if you do not have one yet.

10 2d ago A tokens not measured AGPL-3.0

memory-layer

112

runtimenoteslabs/memory-layer

Plugin Claude Code

Persistent memory with outcome-based learning for AI coding agents. Stores knowledge from coding sessions, learns which memories actually help, and gets smarter over time.

10 3mo ago A tokens not measured original MIT

commitlore

113

MongLong0214/commitlore

Plugin Claude Code

Recorded decisions from git history, delivered to a coding agent before it edits.

9 4d ago A tokens not measured original MIT

commitlore

114

MongLong0214/commitlore

Plugin Claude Code

Recorded decisions from git history, delivered to the agent before it edits. Constraints, alternatives already ruled out, and warnings left by whoever was here last.

9 4d ago A tokens not measured original MIT

pluribus

116

johnnyjoy/pluribus

Plugin Claude Code

First-party Pluribus memory loop for Claude Code: MCP, hooks (session wake-up + prompt recall, optional failure hint), skills, and a recall-first investigator agent. Server owns memory; plugin orchestrates.

9 1mo ago A tokens not measured

unforgit

118

MiguelMedeiros/unforgit

Plugin Claude Code

Persistent repository memory for AI coding agents using MCP tools, repository rules, and durable project knowledge.

9 2d ago A tokens not measured original MIT

tsubasa

119

ramarahmanda/tsubasa

Plugin Claude Code

Plugin marketplace listing 1 plugin: tsubasa.

8 4d ago A tokens not measured original MIT

tsubasa

120

ramarahmanda/tsubasa

Plugin Claude Code

Captain persona: repo-resident domain expert with a git-stored knowledge graph, ambient knowledge capture, and ADR-threaded delegation.

8 4d ago A tokens not measured original MIT