algobot-cli
/algobot-cli
Use for anything AI/agent/conversational built on Algolia: algobot CLI, Agent Studio, RAG systems, conversational product discovery, genAI content generation from search results (carousels, descriptions, headers), chatbots or recommendation agents using Algolia as retrieval, config-as-code workflows, multi-environment deploy (dev/staging/prod), memory and personalization, MCP tool integrations, conversation history / GDPR retention, or adding a chat widget alongside InstantSearch. Trigger on: "algobot", "Agent Studio", "RAG with Algolia", "conversational experience", "AI agent" + Algolia, "gen
Assessment and security
- Files in this package
- 4
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 2
No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use for anything AI/agent/conversational built on Algolia: algobot CLI, Agent Studio, RAG systems, conversational product discovery, genAI content generation from search results (carousels, descriptions, headers), chatbots or recommendation agents using Algolia as retrieval, config-as-code workflows, multi-environment deploy (dev/staging/prod), memory and personalization, MCP tool integrations, conversation history / GDPR retention, or adding a chat widget alongside InstantSearch. Trigger on: "algobot", "Agent Studio", "RAG with Algolia", "conversational experience", "AI agent" + Algolia, "gen
Triggers from the description
Original author description
Use for anything AI/agent/conversational built on Algolia: algobot CLI, Agent Studio, RAG systems, conversational product discovery, genAI content generation from search results (carousels, descriptions, headers), chatbots or recommendation agents using Algolia as retrieval, config-as-code workflows, multi-environment deploy (dev/staging/prod), memory and personalization, MCP tool integrations, conversation history / GDPR retention, or adding a chat widget alongside InstantSearch. Trigger on: "algobot", "Agent Studio", "RAG with Algolia", "conversational experience", "AI agent" + Algolia, "gen
How it works
- When to Use Algobot vs Other Tools
- Setup
- Non-Interactive Mode (Critical for Agents)
- Core Commands
- Config-as-Code Workflow
- Agent Studio Capabilities (via agent config)
- Live Development
- Agent Studio Evaluations
- Global Flags
- Gotchas
SKILL.md preview
---
name: algobot-cli
description: >-
Use for anything AI/agent/conversational built on Algolia: algobot CLI,
Agent Studio, RAG systems, conversational product discovery, genAI content
generation from search results (carousels, descriptions, headers), chatbots
or recommendation agents using Algolia as retrieval, config-as-code
workflows, multi-environment deploy (dev/staging/prod), memory and
personalization, MCP tool integrations, conversation history / GDPR
retention, or adding a chat widget alongside InstantSearch. Trigger on:
"algobot", "Agent Studio", "RAG with Algolia", "conversational experience",
"AI agent" + Algolia, "genAI carousel", "chat widget", or building AI
features on top of Algolia search. Do NOT use for Agent Studio evaluations
or eval-driven agent improvement - use agent-studio-evaluations. Do NOT
use for raw index ops (records, synonyms, settings) - use algolia-cli.
Do NOT use for pure frontend search UI (InstantSearch, autocomplete) with
no AI/agent layer.
license: MIT
metadata:
author: algolia
version: "1.1"
---
# Algobot CLI
[Algolia Agent Studio](https://www.algolia.com/products/ai/agent-studio/) is Algolia's platform for building AI agents — RAG systems, conversational experiences, genAI content generation — with Algolia search and recommendations as the retrieval backbone. `algobot` (`npm install -g algobot-ai`) is its CLI for creating, testing, and deploying agents.
## When to Use Algobot vs Other Tools
| Need | Use |
|------|-----|
| Build/manage AI agents on Algolia (RAG, chatbot, genAI UI) | **algobot-cli** (this skill) |
| Algolia search index ops (records, settings, synonyms) | **algolia-cli** |
| Search queries, analytics, recommendations | **algolia-mcp** |
## Setup
```bash
npm install -g algobot-ai
algobot init # Interactive wizard (creates first agent + profile)
```
Or add a profile manually (CI-safe, non-interactive):
```bash
algobot profiles add --name prod --env prod
```
## Non-Interactive Mode (Critical for Agents)
**The TUI won't render in non-TTY environments** (CI, scripts, agent subprocesses). Use these instead:
```bash
algobot ask "What is your return policy?" # One-shot
algobot interactive --text "hello ||| list my orders ||| /context" # Multi-turn
algobot agents list --jq '.[] | .name' # JSON filtering
```
`--jq` is built-in — no need to install jq separately.
## Core Commands
### Agent Management
```bash
algobot agents list
algobot agents get <agent-id>
algobot agents create --name "Support Bot" --model gpt-4o
algobot agents update <agent-id> --name "New Name"
algobot agents publish <agent-id>
algobot agents unpublish <agent-id>
algobot agents delete <agent-id>
algobot agents copy <id> --from-env dev --to-env prod
```
### Chatting with an Agent
```bash
algobot ask "Find wireless headphones under $100"
algobot --profile staging ask "hello" # Target specific environment
algobot --verbose ask "debug this" # Show full HTTP traces
```
### Profile / Environment Management
```bash
algobot profiles list
algobot profiles add --name dev --env dev
algobot profiles setdefault prod
algobot --profile prod agents list
algobot --env dev agents list
```
## Config-as-Code Workflow
Version-control agent definitions with mustache templates — ideal for repeatable deployments across events, teams, or environments.
```bash
# 1. Scaffold from an existing agent
algobot agents scaffold <agent-id> # → agent-config.json + PROMPT.md
# 2. Preview (API-level kill switch — mutations blocked by construction)
algobot --dry-run agents create --config agent-config.json --var event="Spring 2026"
# 3. Deploy
algobot agents create --config agent-config.json --var event_name="Spring 2026"
# 4. Update + publish in one step
algobot agents update <id> --config agent-config.json --var event_name="Summer 2026" --publish
```
`{{key}}` in JSON fields: JSON-safe escaping. In `.md` instructions: raw substitution.
## Agent Studio Capabilities (via agent config)
Beyond basic chat, Agent Studio agents support:
- **Tools**: Algolia Search, Algolia Browse, Algolia Recommend, client-side tools, and [MCP tools](https://www.algolia.com/doc/guides/algolia-ai/agent-studio/how-to/tools/mcp-tools) (connect CRMs, inventory systems, external APIs alongside Algolia). Manage with `algobot tools list/add/remove`
- **Memory**: Semantic (facts/preferences) and episodic (past interactions) memory across sessions, using `algolia_memorize`, `algolia_ponder`, and `algolia_memory_search` tools. Configure retrieval mode (preload vs preflight) in agent config.
- **Conversation storage**: Persistent history with configurable retention — see `algobot conversations` for export/delete
- **Experimental**: Citation markers `[1][2]` on responses, date injection, response caching — enable in agent config
Use `algobot agents scaffold` to inspect/edit these settings, `algobot --dry-run` to preview before applying.
## Live Development
```bash
algobot agents watch patch.json # Auto-apply patches on file change
```
## Agent Studio Evaluations
`algobot evals` runs Agent Studio Evaluations from the terminal: metric
catalog, profile snapshots, dataset lifecycle, experiment runs, per-case
verdicts, and before/after comparison.
**Version gate:** the `evals` command group (and several `agents`/`conversations`
fixes the eval workflows rely on) requires `algobot-ai` >= 2.1.0 (npm latest).
Probe with `algobot evals metrics list`; if the command is unknown, the
installed `algobot-ai` predates evals: stop and install the release that
ships it (`npm i -g algobot-ai@latest`).
**The evaluation and improvement workflows live in the dedicated
`agent-studio-evaluations` skill**: evaluation dataset creation (including the
real conversation history import recipe), reading results, the
failure-to-knob mapping, and the clone-based "improve my agent" tuning loop,
with the full command map and eval gotchas in its
`references/evaluations.md`. Load that skill for any "evaluate my agent" or
"improve my agent" task; use this skill only for the CLI mechanics (auth,
install, agents/chat/profiles commands).
## Global Flags
| Flag | Effect |
|------|--------|
| `--env dev\|staging\|prod\|local` | Target environment |
| `--profile <name>` | Use named profile |
| `--dry-run` | Preview without mutating (API-enforced) |
| `--verbose` | Full HTTP logs |
| `--jq '<expr>'` | Filter JSON output |
| `--confirm` | Skip exec tool confirmations |
## Gotchas
- **TUI requires TTY.** `algobot` with no args launches the TUI — hangs in scripts. Always use `ask` or `--text` in non-interactive contexts. Recent releases reject unknown subcommands with exit 1 instead of silently becoming a chat message (probe: `algobot frobnicate` must exit 1; see the version gate above). On npm 2.0.0 a typo'd command in a script may still print a chat reply with exit 0.
- **Exit codes are 0/1 only** in v2.0. Can't distinguish "not found" from "auth error" — parse stderr if needed.
- **`--output json` missing on most commands** in v2.0. Use `--jq` or JSON-structured stdout.
- **`algobot init` is interactive.** Don't use in CI — use `profiles add` with flags instead.
- **`prod` resolves to the EU host.** v2.0.0 hardcodes three API hosts — `agent-studio.eu.algolia.com` (prod), `agent-studio-staging.eu.algolia.com` (staging), `conversational-ai-dev.algolia.com` (dev). There is no region flag, and the only environment variables read are `ALGOLIA_APP_ID`, `ALGOLIA_APPLICATION_ID`, `ALGOLIA_API_KEY`, and `ALGOLIA_AGENT_ID` — none of which override the host. If an app's agents are not in EU, `agents list` returns `[]` and `agents get <id>` returns 404 for an agent that is live and serving completions. An admin API key does not change this. Confirm the host with `algobot --verbose agents list` before assuming a credential problem.
- **Credentials are stored in `~/.algobot-profiles`** (encrypted), not `~/.algobot-cookie`. `algobot auth show` was removed in v2.0 — use `algobot profiles list`, or `algobot profiles show <name>` for full detail. Note that `profiles show` prints the API key in plaintext, so avoid it in shared terminals, screenshares, and logs.
- **`--config` auto-discovers `agent-config.json`** in cwd. Explicit: `--config path/to/config.json`.
- **algobot = dev/deploy tool; REST API = production invocation.** Use algobot to build and publish agents; call the Agent Studio completions API directly from your app. Don't guess the endpoint URL — run `algobot agents get <id>` to retrieve it, or check the Agent Studio dashboard.
- **Completions URL has no `/agent-studio` prefix.** Use `agent-studio.<region>.algolia.com/1/agents/<id>/completions?stream=false&compatibilityMode=ai-sdk-4`. `compatibilityMode` is required (omitting → 422). Response: `{ id, role, content }` with `content` as a flat string.
## Reference Docs
- [Command Reference](references/commands.md) — Full flags for every command
- [Config-as-Code Guide](references/config-as-code.md) — Templates, variables, multi-env patterns
Files in this package (4)
- SKILL.md 9 KB
- evals/evals.json 8 KB
- references/commands.md 3 KB
- references/config-as-code.md 3 KB
Versions
The database has no other skills named algobot-cli.
Database snapshot: 13.11.2026 · package version 5b713207a382 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100algolia-agent-studio
Product-specific Algolia Agent Studio implementation, validation, and optimization guidance. Use when planning, building, integrating, or auditing Agent Studio agents, AI-powered conversational experiences, LLM provider setup, Algolia Search tools, client-side tools, MCP tools,… - 90agent-studio-evaluations
Evaluate and improve Algolia Agent Studio agents with the algobot CLI: run Agent Studio evaluations, read pass rates and judge verdicts, create evaluation datasets (including importing the agent's real conversation history as eval cases), compare agent versions before and after… - 90algolia-search
Expert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuning Use when: adding search to, algolia, instantsearch, search api, search functionality. - 90algolia-search
Expert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuning Use when: adding search to, algolia, instantsearch, search api, search functionality. - 90algolia-search
Expert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuning Use when: adding search to, algolia, instantsearch, search api, search functionality. - 100agent-memory-systems
Design tenant-scoped memory, retrieval and retention for agents. Use when planning RAG, conversation history, vector stores or remembering across sessions.