SessionStart
49Hook Claude Code
One of 3 in settings.json
Runs when a session starts on startup, clear and compact, executing session-brief.sh. From techtheist/engram.
148 tagged ai-memory, measured the same way as everything else here.
Browse within: agent-memory 93context-engineering 26artificial-intelligence 20context-management 20knowledge-graph 19ai-coding 16codex-cli 16ai-memory-system 15knowledge-management 15markdown 14agentic-coding 13opencode 13chromadb 12agent-infrastructure 9
Hook Claude Code
One of 3 in settings.json
Runs when a session starts on startup, clear and compact, executing session-brief.sh. From techtheist/engram.
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Read, Edit, Write and MultiEdit tool calls, executing file-read-match.sh. From techtheist/engram.
Hook Claude Code
One of 7 in settings.json
Runs when you submit a prompt, before the agent sees it, running python3 (2 commands). From wusaki0723/memory-template.
Hook Claude Code
One of 7 in settings.json
Runs before the agent uses a tool for Bash tool calls, running python3. From wusaki0723/memory-template.
Hook Claude Code
One of 7 in settings.json
Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, running python3. From wusaki0723/memory-template.
Hook
Part of hypermnesic
Runs when you submit a prompt, before the agent sees it, executing hypermnesic_agent_hook.py with --host. From leonardsellem/hypermnesic.
Hook
Part of troth
Runs before the agent uses a tool for Bash, Edit, Write, MultiEdit, Edit, Write, Bash, Read, Grep, Glob, NotebookEdit, Read, Grep, Glob, Bash, Edit, Write, NotebookEdit, Read, Edit, Write, MultiEdit, NotebookEdit, Grep, Glob, Bash, mcp__plugin_troth_troth-bash__run, Write, Edit, MultiEdit, hashline_edit, Read, Grep…
Hook
Part of troth
Runs after a tool call finishes for Read, Grep, Glob, WebFetch, Read, Grep, Glob, Bash, Bash, Edit, Write, MultiEdit, NotebookEdit, Read, Grep, Glob, Read, Grep, Glob and mcp__.* tool calls, executing mark-read.mjs, cache-populate.mjs, mark-bash.mjs, mark-edit.mjs, post-action-recall.mjs, output-sandbox.mjs and…
Hook
Part of troth
Runs when you submit a prompt, before the agent sees it, executing intent-capture.mjs, constraint-capture.mjs, decision-capture.mjs, topic-shift-detect.mjs, dmn-push.mjs, injector.mjs and voice-shape.mjs via node (7 commands). From xgre1/troth.
Hook
One of 6 in hooks.json
Runs when a session starts, executing bootstrap-runtime.mjs via node. From benediktkraus/dreviho.
Hook
One of 6 in hooks.json
Runs when you submit a prompt, before the agent sees it, executing auto-recall.mjs via node. From benediktkraus/dreviho.
Hook
One of 6 in hooks.json
Runs when the agent finishes a response, executing auto-capture.mjs via node. From benediktkraus/dreviho.
Hook
Part of claude-dejavu
Runs when a session starts, executing dejavu-hook.py via python (2 commands). From HthSolid/claude-dejavu.
Hook
Part of claude-dejavu
Runs before the agent uses a tool for Edit, Write and MultiEdit tool calls, executing dejavu-hook.py via python. From HthSolid/claude-dejavu.
Hook
Part of claude-dejavu
Runs when you submit a prompt, before the agent sees it, executing dejavu-hook.py via python. From HthSolid/claude-dejavu.
Hook
Part of neuron-guard
Runs when a session starts on startup, resume, clear and compact, executing neuron_sessionstart_hook.py via python. From recla93/Neuron.
Hook
Part of knowledge-graph
Runs when a session starts, executing kg-autostart.sh. From mironmax/claudecode-plugins.
Hook
Part of knowledge-graph
Runs when you submit a prompt, before the agent sees it, executing kg-remind.sh. From mironmax/claudecode-plugins.
Hook
Part of knowledge-graph
Runs after a tool call finishes for Read, WebFetch and WebSearch tool calls, executing kg-tool-event.sh. From mironmax/claudecode-plugins.
Hook
Runs when a session starts on startup and resume, running an inline shell check. From ToruAI/megg.
CHANGGELY/claude_codex_gemini_mem
Hook
Part of claude-mem
Runs when a session starts on startup, clear and compact, executing smart-install.js and user-message-hook.js via node (2 commands). From CHANGGELY/claude_codex_gemini_mem.
CHANGGELY/claude_codex_gemini_mem
Hook
Part of claude-mem
Runs when you submit a prompt, before the agent sees it, executing new-hook.js via node. From CHANGGELY/claude_codex_gemini_mem.
CHANGGELY/claude_codex_gemini_mem
Hook
Part of claude-mem
Runs after a tool call finishes, executing save-hook.js via node. From CHANGGELY/claude_codex_gemini_mem.
Hook Claude Code
One of 2 in settings.json
Runs when the agent finishes a response, running an inline shell check. From Jessinra/Lorekeeper.
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: