| Rating |
|---|
| AgentsWisdom score | 73 | 72 |
|---|
| Confidence | high | high |
|---|
| Rank in category | No. 3 of 16 | No. 4 of 16 |
|---|
| Pillars |
|---|
| Adoption & momentum | 93 | 100 |
|---|
| Experts (independent reviews) | 73 | 65 |
|---|
| Crowd (community sample) | 46 | 43 |
|---|
| Community posts sampled | 29 | 21 |
|---|
| Experts vs crowd | Crowd cooler by 27 | Crowd cooler by 22 |
|---|
| Adoption |
|---|
| GitHub stars | 91k | n/e |
|---|
| npm weekly downloads | n/e | n/e |
|---|
| PyPI monthly downloads | n/e | n/e |
|---|
| VS Code installs | n/e | 78M |
|---|
| Reported users | n/e | 50M |
|---|
| Reported customer organisations | n/e | n/e |
|---|
| Releases, last 90 days | 46 | 100 |
|---|
| Benchmarks (shown, not scored) |
|---|
| Terminal-Bench 2.0 | not listed | not listed |
|---|
| SWE-bench | not listed | not listed |
|---|
| Independent reviews | 8 | 7 |
|---|
| Trust & safety |
|---|
| Overall grade | A | B |
|---|
| Permission model | A | B |
|---|
| Data access scope | A | A |
|---|
| Data storage | A | n/e |
|---|
| Data retention & training | A | C |
|---|
| Incident history | C | n/e |
|---|
| Compliance | B | A |
|---|
| Transparency | A | B |
|---|
| Price |
|---|
| Price | Free, paid from $10 | Free, paid from $10 |
|---|
| Plans | - Personal: Free
- Pro: $10 / monthly
- Business: $30 / monthly
| - Free: Free
- Pro: $10 / monthly
- Pro+: $39 / monthly
- Max: $100 / monthly
- Business: $19 / monthly per user
- Enterprise: $39 / monthly per user
|
|---|
| Product |
|---|
| Category | Coding agents | Coding agents |
|---|
| Maker | Zed Industries | GitHub (Microsoft) |
|---|
| Licence | GPL-3.0-or-later | proprietary |
|---|
| Use it via | Desktop app | IDE extension, CLI, Desktop app, Web app, Mobile app, Chat apps, API |
|---|
| Runs on | macos, linux, windows | macos, windows, linux, web |
|---|
| Models it drives | Claude, GPT, Gemini, DeepSeek, Mistral, Amazon Bedrock, GitHub Copilot models, any model via OpenRouter / Vercel gateway, local via Ollama / LM Studio, external ACP agents (Claude Agent, Codex, Gemini CLI, OpenCode, Copilot, Cursor, Pi, Poolside) | GPT, Claude, Gemini, Grok, Kimi (open-weight), automatic model routing |
|---|
| Key features | - Agent Panel with built-in agent: file edits, terminal, fetch, MCP tools
- Parallel agent threads in a Threads Sidebar, optional per-thread Git worktree isolation
- Hosts external agents over the Agent Client Protocol, with an ACP Registry for installing them
- Per-tool permission rules (allow / confirm / deny) with pattern matching on commands and paths
- OS-level sandbox for terminal and fetch tools on by default since v1.14 (Seatbelt on macOS, Bubblewrap on Linux, WSL on Windows)
- Checkpoints to restore code, multibuffer review of agent edits, follow-the-agent view
- Agent profiles to choose which built-in and MCP tools are available
- Edit predictions (inline next-edit completions) alongside the agent
| - Agent mode in VS Code, Visual Studio and JetBrains with an Agents window and local Dev Container execution
- Copilot cloud agent: assign an issue, agent works in an ephemeral GitHub Actions environment and opens one pull request per task
- Copilot CLI terminal agent (npm @github/copilot) with experimental semantic model routing
- Copilot code review and Autofix on pull requests
- Copilot app with Jira, Sentry, Slack and Microsoft Teams integrations
- Assisted approvals and local sandboxing for agent sessions (public preview, Sept 2026)
- Third-party coding agents (Claude, OpenAI) available on Pro+ and above
- Token-based GitHub AI Credits billing since June 2026
|
|---|
| Verdicts |
|---|
| Praised for | - Can run and switch between several agents (built-in and ACP external agents) in one editor window
- Parallel agent threads with worktree isolation are praised by users moving from single-thread agent workflows
- Fast, lightweight editor that users keep even when they run agents elsewhere
- Free bring-your-own-key use and external agents on the $0 plan
| - Broad model choice under one enterprise contract, including open-weight models, is cited as its enterprise advantage (HN, July 2026).
- Reach and distribution: 50 million users and deep GitHub integration (Microsoft FY26 Q4 call; GitHub discussion users citing GHE integration).
- Independent reviewers find it pays off for high-volume, well-tested code in mainstream languages (Netguru, Sept 2026).
|
|---|
| Criticised for | - Agent UI and parallel-agent layout described as confusing by several users after the April 2026 changes
- Built-in agent seen by some reviewers and users as less capable or less turnkey than Cursor, Claude Code or OpenCode
- ACP-hosted external agents reported as buggy or limited (buffer not refreshing, lost LSP access, never-ending runs)
- Diff/code-review tooling for reviewing agent output considered insufficient by some users
| - June 2026 move to usage-based AI Credits was widely read as a large effective price increase; many users said they would cancel (HN and GitHub Community, April 2026).
- Trust damage from Copilot inserting promotional 'tips' into pull requests in March 2026, later withdrawn.
- Individual-plan interaction data used for model training by default since 24 April 2026 unless users opt out.
- Real-world suggestion acceptance reported well below GitHub's published figures (Netguru, Sept 2026).
|
|---|
| Evidence |
|---|
| Evidence collected | 26 Sept 2026 | 26 Sept 2026 |
|---|
| Sources cited | 10 | 5 |
|---|
