86 tagged ai-memory-system, measured the same way as everything else here.
Browse within: agentic-coding 48ai-developer-tools 48ai-governance 48agentic 20agentic-framework 20agentic-os 20harness-execution-layer 20ai-awesome 8ai-memory 8Memory Management 6cli-tool 6
Skill Claude CodeCodex
Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…
Skill Claude CodeCodex
How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and…
Skill Claude CodeCodex
Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, dbquery, and exposing a script as an API.
digipulse-engineering/GAAI-framework
Skill Claude CodeCodex
Takes surface scan results, optional LLM synthesis open-question entries, and optional tree-sitter AST signals to score project ambiguities (1-10). Outputs structured ambiguityfeed for smart-question-generator. Pure heuristic — no LLM calls. Designed for Stage 3.5 of the /gaai:bootstrap pipeline (between LLM synthesis…
digipulse-engineering/GAAI-framework
Skill Claude CodeCodex
Construct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM. Parse and validate the response into 6-8 structured memory entries with clarity tags and source traceability. Used as Stage 3 of the /gaai:bootstrap pipeline.
digipulse-engineering/GAAI-framework
Skill Claude CodeCodex
Takes aggregated ambiguity insights from the LLM synthesis stage and produces ≤5 ranked questions to surface to the user. Applies a two-layer anti-fabrication filter (pre-LLM exclusion of score<3 insights + post-LLM structural strip) so that Q&A surfaces only genuine ambiguities. Used as Stage 4 of the /gaai:bootstrap…
Skill Claude CodeCodex
Use when you have access to Recallium MCP tools. Provides guidance on memory storage, search, and knowledge management. CRITICAL - invoke the MCP tool recallium at session start, store memories after EVERY substantive interaction, and honor global rules.
Skill Claude CodeCodex
Seed or top up this project's Engram graph from the existing codebase — an explicit, user-invoked digestion of the current working tree into typed memory nodes (decisions, principles, cautions, problems, insights, intents). Use when the user says "digest this project", "ingest the codebase into memory", "seed the…
Skill Claude CodeCodex
Read and write the project's durable reasoning memory (decisions, principles, cautions, problems, insights) through the Engram MCP tools. Recall relevant memory before non-trivial work; capture only durable, high-value knowledge silently at natural stopping points; keep the graph honest (judge suspects, close answered…
Skill Claude CodeCodex
Read and write the project's durable reasoning memory (decisions, principles, cautions, problems, insights) through the Engram MCP tools. Recall relevant memory before non-trivial work; capture decisions and knowledge silently at natural stopping points; keep the graph honest (judge suspects, close answered problems…
Skill Claude CodeCodex
Use this skill when working in a project that has a RunawayContext v3 install. It loads the project's brief from the auto-generated Tier 3 markdown, queries knowledge.db for relevant lessons and chunks, and routes writes through the contract-enforced Client (HR-2 / HR-3 / HR-9). Trigger when the conversation enters a…
Skill Claude CodeCodex
Gives an agent persistent long-term memory backed by a local sparse-vector file. Use when the agent should recall past context, learn from interactions, or incorporate reinforcement feedback. Relevant for tasks mentioning memory, recall, learning, history, or context retention.
Skill Claude CodeCodex
A skill that builds a three-layer knowledge base for a collection of files. It groups files by subject and stores summaries and indexes in a .kb/ folder.
Skill Claude CodeCodex
A read-only check for whether a knowledge base has fallen out of date with the files it was built from. It compares recent Git changes with the knowledge base's last refresh record.
Skill Claude CodeCodex
A documentation tool that turns a completed project plan into one durable decision record in the project knowledge base. It keeps the original plan unchanged.
Skill Claude CodeCodex
Persistent, project-aware memory for AI coding agents. Use thoughtline whenever you make a decision, fix a bug, learn something non-obvious, or need to recall prior work.