{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_kel","slug":"kel","name":"Kel","type":"cli","url":"https://kel.qainsights.com","page_url":"https://unfragile.ai/kel","categories":["cli-tools"],"tags":[],"pricing":{"model":"free","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_kel__cap_0","uri":"capability://text.generation.language.interactive.ai.chat.within.terminal.shell","name":"interactive ai chat within terminal shell","description":"Embeds a conversational AI interface directly into the command line environment, allowing developers to query an LLM without context-switching to a browser. The tool maintains a chat session within the terminal, processing natural language queries and returning responses inline with shell output. Integration appears to be a standalone CLI binary that spawns an interactive REPL-like interface rather than a shell plugin or function.","intents":["Ask quick questions about command syntax without leaving the terminal","Get debugging help for shell errors in real-time","Brainstorm solutions to DevOps problems without alt-tabbing to ChatGPT","Maintain conversation context across multiple related questions in a single session"],"best_for":["Terminal-native developers who spend 8+ hours daily in shell environments","DevOps engineers debugging infrastructure issues","System administrators automating repetitive tasks"],"limitations":["No documented shell-specific optimizations — unclear if it integrates with bash history, aliases, or environment variables","Session context appears limited to conversation history only — no working directory or git branch awareness documented","Installation method and shell compatibility matrix not documented — may require manual setup per shell type"],"requires":["API key for OpenAI, Anthropic, or local Ollama instance","Operating system and runtime dependencies unknown — likely requires Node.js, Python, or Go runtime"],"input_types":["natural language text queries","uploaded files for artifact-based Q&A"],"output_types":["natural language responses","suggested shell commands","explanatory text"],"categories":["text-generation-language","cli-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_kel__cap_1","uri":"capability://tool.use.integration.multi.provider.llm.backend.selection","name":"multi-provider llm backend selection","description":"Abstracts LLM provider selection through a configuration layer supporting OpenAI, Anthropic, and Ollama (local models). Developers supply their own API keys and can switch providers without changing the CLI interface. The tool routes requests to the selected provider's API endpoint, handling authentication and response parsing transparently.","intents":["Use OpenAI GPT-4 for complex reasoning tasks while keeping costs low","Switch to Anthropic Claude for tasks requiring longer context windows","Run Ollama locally for privacy-sensitive work without sending data to cloud APIs","Avoid vendor lock-in by maintaining flexibility across LLM providers"],"best_for":["Teams with existing relationships with multiple LLM providers","Organizations with data privacy requirements favoring local inference","Cost-conscious developers optimizing for token efficiency"],"limitations":["No documented cost tracking or token usage visibility — developers must monitor spending through provider dashboards separately","Provider-specific features (e.g., vision models, function calling) not documented — unclear which capabilities are available per provider","API key management mechanism not documented — unclear if credentials are encrypted at rest or stored in plaintext config files","No automatic fallback or retry logic documented if primary provider is unavailable"],"requires":["API key for at least one of: OpenAI, Anthropic, or local Ollama instance running on network","Network connectivity to cloud providers (unless using Ollama exclusively)"],"input_types":["provider selection configuration","API credentials"],"output_types":["routed API requests","provider-specific responses"],"categories":["tool-use-integration","llm-orchestration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_kel__cap_2","uri":"capability://memory.knowledge.file.artifact.upload.and.contextual.q.a","name":"file artifact upload and contextual q&a","description":"Allows developers to upload files (code, logs, documentation, etc.) into the chat session and ask questions about their contents. The tool loads the artifact into context and processes queries against it, enabling file-based analysis without manual copy-paste. Implementation likely uses the LLM's context window to embed file contents and process natural language queries over them.","intents":["Ask questions about a codebase file without manually copying it into chat","Analyze error logs or stack traces by uploading them directly","Get explanations of unfamiliar code or configuration files","Debug issues by providing full context (code + error output) in a single interaction"],"best_for":["Developers debugging complex issues requiring full file context","Teams reviewing code or logs collaboratively through a shared CLI session","DevOps engineers analyzing configuration files or deployment logs"],"limitations":["Artifact size limits not documented — unclear if there are file size constraints or context window limits","No mention of binary file support — likely limited to text-based files (code, logs, config)","No version control or artifact history — uploaded files appear to be ephemeral within a session","No batch upload capability documented — appears to require uploading files one at a time","Security implications of uploading files to cloud LLM providers not addressed"],"requires":["File accessible on local filesystem","API key for selected LLM provider (file contents will be sent to provider)"],"input_types":["text files (code, logs, config, documentation)","natural language queries about file contents"],"output_types":["analysis and explanations","code suggestions","debugging insights"],"categories":["memory-knowledge","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_kel__cap_3","uri":"capability://memory.knowledge.session.based.conversation.memory","name":"session-based conversation memory","description":"Maintains conversation history within a single CLI session, allowing multi-turn interactions where the LLM retains context from previous messages. Each message in the session is appended to the conversation history and sent to the LLM, enabling follow-up questions and iterative refinement without re-explaining context.","intents":["Ask follow-up questions that reference earlier parts of the conversation","Iteratively refine solutions through multiple back-and-forth exchanges","Build on previous explanations without restating the problem","Maintain context across related debugging or coding tasks in a single session"],"best_for":["Developers working through complex problems requiring iterative refinement","Teams pair-programming or collaborating through a shared terminal session","Debugging workflows where each step builds on previous findings"],"limitations":["Session memory is ephemeral — conversation history is lost when the CLI session ends, with no documented persistence mechanism","Context window constraints not documented — unclear how many turns of conversation can be maintained before hitting LLM token limits","No session export or logging capability documented — conversations cannot be saved for later reference or audit","No multi-session context sharing — each new CLI invocation starts with blank history"],"requires":["Active CLI session","Continuous network connectivity to LLM provider"],"input_types":["natural language queries","follow-up questions"],"output_types":["contextual responses","refined suggestions based on conversation history"],"categories":["memory-knowledge","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_kel__cap_4","uri":"capability://tool.use.integration.local.llm.inference.via.ollama.integration","name":"local llm inference via ollama integration","description":"Supports Ollama as a backend for running open-source language models locally without cloud API calls. Developers can configure Kel to route requests to a local Ollama instance, enabling offline-first workflows and eliminating data transmission to external servers. Implementation likely uses HTTP requests to Ollama's local API endpoint.","intents":["Run AI assistance completely offline for privacy-sensitive work","Avoid API costs by using free open-source models locally","Maintain full control over data without sending it to cloud providers","Experiment with different open-source models without cloud subscription costs"],"best_for":["Organizations with strict data privacy or compliance requirements","Cost-conscious developers avoiding cloud API charges","Teams working on sensitive code or infrastructure that cannot leave the network","Developers experimenting with open-source models"],"limitations":["Requires Ollama installation and model download on local machine — adds setup complexity and disk space requirements","Model quality and speed depend on local hardware — no GPU acceleration may result in slow inference","No documented model selection or switching mechanism — unclear how developers choose between installed Ollama models","Ollama availability and network configuration not documented — unclear if it supports remote Ollama instances or only localhost","Model-specific capabilities (context window, instruction format) not abstracted — developers must understand each model's limitations"],"requires":["Ollama installed and running locally (https://ollama.ai)","At least one language model downloaded via Ollama (e.g., llama2, mistral)","Sufficient disk space for model files (typically 4-40GB depending on model size)","Hardware capable of running inference (GPU recommended for reasonable performance)"],"input_types":["natural language queries","file artifacts"],"output_types":["local model responses","no external API calls"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_kel__cap_5","uri":"capability://text.generation.language.free.tier.with.no.authentication.barrier","name":"free tier with no authentication barrier","description":"Offers a free tier that allows developers to use the tool without payment or complex signup processes. The free tier appears to support basic chat functionality with uploaded artifacts, though specific usage limits are not documented. This lowers the barrier to entry for developers experimenting with AI-assisted terminal workflows.","intents":["Try AI-assisted terminal workflows without financial commitment","Evaluate whether the tool fits into existing development practices","Experiment with different LLM providers before committing to paid plans","Introduce team members to AI-assisted development with minimal friction"],"best_for":["Individual developers and solo practitioners","Teams evaluating AI tools before enterprise adoption","Open-source developers with limited budgets","Students and learners exploring AI-assisted development"],"limitations":["Free tier scope not documented — unclear what features or usage limits apply","No pricing page or tier comparison provided — unclear if paid tiers exist or what they offer","Monetization model unclear — unclear how the tool sustains development if free tier is primary offering","No documented rate limiting or quota enforcement for free tier"],"requires":["No payment method required for free tier","API key for LLM provider (OpenAI, Anthropic, or Ollama) still required"],"input_types":["natural language queries","file artifacts"],"output_types":["chat responses","analysis and suggestions"],"categories":["text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_kel__cap_6","uri":"capability://tool.use.integration.openai.assistants.api.integration","name":"openai assistants api integration","description":"Integrates with OpenAI's Assistants API, enabling developers to leverage assistant-specific features like persistent threads, file handling, and code execution capabilities. The tool routes requests to the Assistants API endpoint rather than the standard chat completion API, potentially providing richer interaction patterns and stateful conversation management.","intents":["Use OpenAI Assistants features (persistent threads, file analysis) through the CLI","Leverage code execution capabilities for running and testing code suggestions","Maintain stateful conversations across multiple CLI invocations using assistant threads","Access assistant-specific tools and integrations not available in standard chat API"],"best_for":["Developers already using OpenAI Assistants API in other contexts","Teams requiring persistent conversation state across sessions","Workflows involving code execution or file analysis at scale"],"limitations":["Assistants API pricing and usage limits not documented — unclear if it's more expensive than standard chat API","Thread persistence mechanism not documented — unclear if threads are stored in OpenAI's system or locally","Code execution capabilities not documented — unclear what languages or sandboxing is supported","No documentation on assistant configuration or customization through the CLI","Assistants API availability and feature set may lag behind standard chat API"],"requires":["OpenAI API key with Assistants API access","Active OpenAI account with billing enabled"],"input_types":["natural language queries","file artifacts","code snippets"],"output_types":["assistant responses","code execution results","file analysis"],"categories":["tool-use-integration","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_kel__cap_7","uri":"capability://tool.use.integration.bring.your.own.api.key.credential.model","name":"bring-your-own-api-key credential model","description":"Requires developers to supply their own API keys for LLM providers rather than using a centralized authentication system. Developers configure their credentials (OpenAI, Anthropic, Ollama) and the tool uses them to authenticate requests. This model shifts credential management responsibility to the user but avoids the need for Kel to manage API keys or billing.","intents":["Use existing API keys and billing relationships with LLM providers","Avoid creating new accounts or sharing billing information with third parties","Maintain full control over API key management and rotation","Integrate with existing organizational API key management practices"],"best_for":["Developers with existing OpenAI or Anthropic accounts","Organizations with strict credential management policies","Teams using Ollama for local inference (no API key needed)"],"limitations":["Credential storage mechanism not documented — unclear if keys are encrypted at rest or stored in plaintext","No documented key rotation or expiration management","Developers responsible for securing their own API keys — risk of accidental exposure in shell history or config files","No centralized billing or usage tracking through Kel — developers must monitor costs through provider dashboards","No documented support for credential environment variables or secure credential stores (e.g., 1Password, AWS Secrets Manager)"],"requires":["API key for at least one LLM provider (OpenAI, Anthropic, or local Ollama)","Mechanism to securely store and provide credentials to the CLI"],"input_types":["API credentials","provider configuration"],"output_types":["authenticated API requests"],"categories":["tool-use-integration","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":42,"verified":false,"data_access_risk":"high","permissions":["API key for OpenAI, Anthropic, or local Ollama instance","Operating system and runtime dependencies unknown — likely requires Node.js, Python, or Go runtime","API key for at least one of: OpenAI, Anthropic, or local Ollama instance running on network","Network connectivity to cloud providers (unless using Ollama exclusively)","File accessible on local filesystem","API key for selected LLM provider (file contents will be sent to provider)","Active CLI session","Continuous network connectivity to LLM provider","Ollama installed and running locally (https://ollama.ai)","At least one language model downloaded via Ollama (e.g., llama2, mistral)"],"failure_modes":["No documented shell-specific optimizations — unclear if it integrates with bash history, aliases, or environment variables","Session context appears limited to conversation history only — no working directory or git branch awareness documented","Installation method and shell compatibility matrix not documented — may require manual setup per shell type","No documented cost tracking or token usage visibility — developers must monitor spending through provider dashboards separately","Provider-specific features (e.g., vision models, function calling) not documented — unclear which capabilities are available per provider","API key management mechanism not documented — unclear if credentials are encrypted at rest or stored in plaintext config files","No automatic fallback or retry logic documented if primary provider is unavailable","Artifact size limits not documented — unclear if there are file size constraints or context window limits","No mention of binary file support — likely limited to text-based files (code, logs, config)","No version control or artifact history — uploaded files appear to be ephemeral within a session","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.31666666666666665,"quality":0.67,"ecosystem":0.15000000000000002,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.28,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:31.446Z","last_scraped_at":"2026-04-05T13:23:42.560Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=kel","compare_url":"https://unfragile.ai/compare?artifact=kel"}},"signature":"Rsjs7BlM4e4rqaccPC3lpdGdjGsT4C/8pMkyW+Id9mQexmcqTDrLdwgkbTq5UdwqB+wDCc1zGouYrTGTYPcWCw==","signedAt":"2026-06-22T23:09:42.974Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/kel","artifact":"https://unfragile.ai/kel","verify":"https://unfragile.ai/api/v1/verify?slug=kel","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}