llm hooks

langgenius/dify

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, running npx -y [email protected]. From langgenius/dify.

mem0ai/mem0

Hook

Runs when a session starts on startup, resume and compact, executing ensure_deps.sh and on_session_start.sh (2 commands). From mem0ai/mem0.

mem0ai/mem0

Hook

Runs before the agent uses a tool for Write, Edit, MultiEdit, mcp__mem0__add_memory, mcp__plugin_mem0_mem0__add_memory, mcp__mem0__search_memories, mcp__plugin_mem0_mem0__search_memories, mcp__mem0__get_memories, mcp__plugin_mem0_mem0__get_memories, mcp__mem0__delete_all_memories…

mem0ai/mem0

Hook

Runs after a tool call finishes for mcp__mem0__.*, mcp__plugin_mem0_mem0__.* and Bash tool calls, executing on_post_tool_use.sh and on_bash_output.sh (2 commands). From mem0ai/mem0.

MemPalace/mempalace

Hook Claude Code

Runs when the agent finishes a response, executing mempal-stop-hook.sh via bash. From MemPalace/mempalace.

MemPalace/mempalace

Hook Claude Code

Runs when a session ends, executing mempal-session-end-hook.sh via bash. From MemPalace/mempalace.

MemPalace/mempalace

Hook Claude Code

Runs before the context is compacted, executing mempal-precompact-hook.sh via bash. From MemPalace/mempalace.

promptfoo/promptfoo

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From promptfoo/promptfoo.

promptfoo/promptfoo

Hook Claude Code

Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From promptfoo/promptfoo.

fathah/hermes-desktop

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, running lat hook claude UserPromptSubmit. From fathah/hermes-desktop.

fathah/hermes-desktop

Hook Claude Code

Runs when the agent finishes a response, running lat hook claude Stop. From fathah/hermes-desktop.

areal-project/AReaL

Hook Claude Code

Runs after a tool call finishes for Write and Edit tool calls, executing check-expert-update.sh. From areal-project/AReaL.

jihe520/MathModelAgent

Hook Claude Code

Runs after a tool call finishes for Edit and Write tool calls, executing hook_lint.sh via bash with --show-toplevel. From jihe520/MathModelAgent.

basicmachines-co/basic-memory

Hook

Runs when a session starts, executing session_start.py via uv with --quiet and --script. From basicmachines-co/basic-memory.

basicmachines-co/basic-memory

Hook

Runs before the context is compacted, executing pre_compact.py via uv with --quiet and --script. From basicmachines-co/basic-memory.

langwatch/langwatch

Hook

Runs when a session starts, executing session-context.mjs and session-guidance.mjs via node (2 commands). From langwatch/langwatch.

langwatch/langwatch

Hook

Runs when the agent finishes a response, executing session-context.mjs via node. From langwatch/langwatch.

av/harbor

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From av/harbor.

moltis-org/moltis

Hook Claude Code

Runs when a session ends, executing save-session.sh. From moltis-org/moltis.

moltis-org/moltis

Hook Claude Code

Runs when the agent finishes a response, executing rename-plan.sh. From moltis-org/moltis.

LLMQuant/quant-mind

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing pre_tool_use_no_bypass.py via python3. From LLMQuant/quant-mind.

pchalasani/claude-code-tools

Hook

Runs when you submit a prompt, before the agent sees it, executing share_hook.py via bash. From pchalasani/claude-code-tools.

PolyArch/humanize

Hook

Runs when you submit a prompt, before the agent sees it, executing loop-plan-file-validator.sh. From PolyArch/humanize.

PolyArch/humanize

Hook

Runs before the agent uses a tool for Write, Edit, Read and Bash tool calls, executing loop-write-validator.sh, loop-edit-validator.sh, loop-read-validator.sh and loop-bash-validator.sh (4 commands). From PolyArch/humanize.