Memory and context agents

1,066 tagged Memory and context, measured the same way as everything else here.

Browse within: agent-memory 43knowledge-management 34agent-orchestration 27obsidian 27ai-memory 26context-engineering 22knowledge-graph 22agent-framework 21claude-code-skills 20gemini-cli 20knowledge-base 20ai-assistant 19Multi-Agent 18markdown 18

memory-compressor

121

yucai0302/memory-loop

Agent

Compresses the project memory hot layer when it grows too large. Reads MEMORY.md and schema.yaml, archives older entries into archive.md, and rewrites MEMORY.md keeping only recent high-value entries. Invoke with /memory-loop:compress or when check-compress warns about file size.

30 2mo ago A 60 tokens

philngt/contextd

Agent Claude Code

Compatibility adapter đọc/summarize context artifact từ contextd context; canonical source là .contextd/context/current-task.json, markdown chỉ là render. KHÔNG tự invent retrieval rules.

29 13d ago A 43 tokens original MIT

contextd-curator

123

philngt/contextd

Agent Claude Code

Cập nhật knowledge repo sau khi code thay đổi — pattern mới, contract mới, service mới, ADR mới. DÙNG KHI user gọi /update-contextd hoặc khi cần đồng bộ knowledge sau merge. KHÔNG DÙNG để chỉnh code project.

29 13d ago A 59 tokens original MIT

panaversity/agentfactory-business-plugins

Agent

Part of hr-operations

Persistent agent that automatically initiates structured knowledge capture when an employee resignation is confirmed. Calibrates capture intensity to the employee's role, tenure, and institutional knowledge risk. Ensures knowledge articles are produced and filed before the last day. Activate for: departure knowledge…

28 5mo ago A 80 tokens original Apache-2.0

context-manager

125

gensecaihq/MCP-Developer-SubAgent

Agent Claude Code

Manages context and state across MCP development sessions, coordinates multi-agent workflows, and preserves architectural decisions.

28 1y ago A 22 tokens original MIT

memory-orchestrator

126

anthony-maio/mnemos

Agent

Part of mnemos-memory

Biomimetic memory orchestrator. Retrieve before complex work, store high-salience facts during execution, and consolidate before handoff.

27 5mo ago A 33 tokens original MIT

mnemos-curator

127

anthony-maio/mnemos

Agent

Part of mnemos-memory

Curate durable Mnemos memory after meaningful work. Use proactively to store stable repo facts, decisions, environment constraints, and recurring bug patterns, then consolidate memory.

27 5mo ago A 37 tokens original MIT

mnemos-recall

128

anthony-maio/mnemos

Agent

Part of mnemos-memory

Recall the most relevant Mnemos context before substantial work. Use proactively at task start to surface durable repo facts, environment constraints, prior fixes, and stable preferences that matter to the current task.

27 5mo ago A 43 tokens original MIT

observer

130

x-cmd/skill

Agent

Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency. v2.1 adds project-scoped instincts.

26 1mo ago A 33 tokens original Apache-2.0

git-learner

131

RohiRIK/OpenLtm

Agent

Part of openltm

Mines durable engineering memories from git commit diffs and stores them in LTM. Use to onboard a repo, backfill history after enabling gitLearn, or harvest patterns after a sprint. Reads diffs in its own context so raw git output never reaches the main thread.

26 25d ago A 60 tokens original MIT

Inbox Classifier

132

onebrain-ai/onebrain

Agent Claude Code

Part of onebrain

Classifies an inbox note and recommends target folder, subfolder, filename, and wikilinks for /consolidate.

25 5d ago A 28 tokens original Apache-2.0

Knowledge Linker

133

onebrain-ai/onebrain

Agent Claude Code

Part of onebrain

Scans vault for unlinked notes and suggests wikilink connections between related content.

25 5d ago A 20 tokens original Apache-2.0

Link Suggester

134

onebrain-ai/onebrain

Agent Claude Code

Part of onebrain

After a new note is written, scans the vault for related notes and automatically adds up to 3 wikilinks under a ## Related section.

25 5d ago A 33 tokens original Apache-2.0

mb-doctor

135

fockus/skill-memory-bank

Agent

Memory Bank diagnostician — finds and fixes internal inconsistencies across core files (roadmap.md ↔ checklist.md ↔ status.md ↔ backlog.md ↔ plans/). Invoked by /mb doctor. Uses deterministic mb-drift.sh first.

25 1mo ago A 54 tokens original MIT

mb-manager

136

fockus/skill-memory-bank

Agent

Memory Bank manager — maintains .memory-bank/ (context, search, note, tasks, actualize). Invoked by /mb context|search|note|tasks|update|done and PreCompact hook.

25 1mo ago A 46 tokens original MIT

clnode-curator

137

SierraDevsec/clnode

Agent Claude Code

You are the knowledge curator for this project's agent swarm. You manage what the team knows, ensure quality of accumulated knowledge, and set standards that all agents follow.

25 6mo ago A 43 tokens

epic-summarizer

138

nguyenthienthanh/aura-frog

Agent

Part of aura-frog

Distills a completed Epic (T2 Feature done) into a permanentmemory.md section. Captures architectural decisions, gotchas, anti-patterns, conflicts. Writes ONLY to .claude/memory/. Confidence-scored: items below 0.7 land in a Tentative subsection.

24 8d ago A 64 tokens original MIT

memory_directory

140

shinerio/SkillFlow

Agent

This file records the default memory directories used by SkillFlow's built-in agent profiles. These paths match the defaults in core/agentintegration/domain/defaults.go.

24 3d ago A 0 tokens original MIT

knowledge-reviewer

141

DFilipeS/praxis

Agent

Searches documented learnings from previous development cycles for relevant insights. Use when planning or starting new work to avoid repeating past mistakes.

24 5mo ago A 30 tokens

compaction-reviewer

142

lossless-claude/lcm

Agent

Part of lcm

Use this agent to review compaction quality — checks whether summaries accurately preserve important information from source messages. Use proactively after compaction completes, or when the user asks about summary quality. Examples.

24 21d ago A 43 tokens original MIT

buddy

143

pallavrustogi/Buddy

Agent

Friendly onboarding agent that explains the repo like you are new. Maintains a portable .buddy/ knowledge base (Markdown + small JSON) at the repo root so every clone benefits.

24 6d ago A 38 tokens copy · 92% MIT

hints

144

beycom/onetool-mcp

Agent

Primary use: Load this file for immediate context about the project.

23 6d ago A 0 tokens GPL-3.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: