percept-ambientContinuously captures and summarizes ambient conversations to build a local knowledge graph for context-aware assistance without explicit commands.
Install via ClawdBot CLI:
clawdbot install jarvis563/percept-ambientGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/GetPercept/perceptAudited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
The agent passively captures discussions during meetings and calls, building a knowledge graph of projects, stakeholders, and decisions. When an executive asks for updates on a client project, the agent provides context packets with relevant conversations and relationships, enhancing briefing accuracy without manual note-taking.
In a hospital or clinic, the agent runs in the background during staff handovers and patient consultations, extracting entities like medical conditions, treatments, and personnel. It enables quick retrieval of patient history and team discussions, supporting continuity of care and reducing information gaps.
During legal team meetings and client interactions, the agent continuously logs conversations, identifying key entities such as cases, clients, and legal precedents. Lawyers can query for past discussions on specific cases, speeding up research and ensuring consistent case strategy based on ambient context.
In research labs or academic settings, the agent monitors discussions among researchers, tracking projects, methodologies, and collaborators. When a researcher inquires about prior experiments or team insights, the agent delivers context packets with summarized conversations and entity relationships, facilitating knowledge sharing.
The agent operates in the background during support calls and team huddles, learning about common issues, products, and customer profiles. Support agents can ask for context on recurring problems or customer history, improving response times and personalization without disrupting workflows.
Offer the skill as a premium add-on for AI agent platforms, charging a monthly fee per user or organization. Revenue comes from tiered plans based on features like retention periods, dashboard access, and integration support, targeting businesses needing continuous context awareness.
Sell customized licenses to large corporations for on-premise deployment, including dedicated support, training, and privacy controls. Revenue is generated through one-time setup fees and ongoing maintenance contracts, appealing to industries with strict data security requirements.
Provide a free basic version with limited retention and search capabilities, then upsell to paid tiers for advanced features like vector search, extended TTL, and real-time analytics. Revenue streams from upgrades and add-ons, attracting individual users and small teams initially.
💬 Integration Tip
Ensure percept-listen and percept-summarize skills are properly configured and running to enable continuous data capture and entity extraction for optimal performance.
Scored Apr 19, 2026
Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions wi...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
Automatically prune and compact agent memory files to prevent unbounded growth. Circular buffer for logs, importance-based retention for state, and configura...
Founder onboarding interview that captures company context across 7 dimensions. Invoke with /cs:setup for initial interview or /cs:update for quarterly refre...
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vib...
Expert skill for memory-lancedb-pro — a production-grade LanceDB-backed long-term memory plugin for OpenClaw agents with hybrid retrieval, cross-encoder rera...