Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for engineering teams, SRE / DevOps teams, product teams, and AI-coding enthusiasts who want an open-source, self-hostable, BYOK alternative to Anthropic's paid Claude-in-Slack — Slack-native AI agent that reads threads, calls tools, and renders rich results inline (tables, charts, breakdowns) without per-seat pricing or lock-in. The durable differentiator is the AG-UI agent runtime (Copilo
Who should use it
Who should skip it
Skip CopilotKit/OpenTag if the source repository or demo is inactive, unmaintained, or no longer matches the description shown here.
About this signal
CopilotKit/OpenTag is tracked by RepoRadar as a open-source claude-in-slack alte in the Agent Platform / Slack Integration section. It was first seen on 2026-07-04 and last updated on 2026-07-04. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for CopilotKit/OpenTag are workflow potential (9.5) and practical usefulness (9.0), while maturity (6.3) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned CopilotKit/OpenTag a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
The CopilotKit/OpenTag repo's `pnpm install` from this repo currently lights up only after the bot SDK packages finish publishing to npm — the dependable install path today is from the CopilotKit monorepo as a first-class example at `examples/slack`; treat the standalone install path as preview-quality until the bot SDK packages land on npm; The Slack-native path requires creating a Slack app at `https://api.slack.com/apps` and copying `slack-app-manifest.yaml` into the manifest editor — the team must own a Slack workspace they can install the bot to; and the bot's permission scope is determined by the manifest (audit the Block Kit scopes before production deploy).