{"schemaVersion":"agenova.agent-machine-projection.v4","entity":{"id":"agt_zed_agent","type":"ai_agent","name":"Zed Agent","slug":"zed-agent","provider":"Zed Industries","canonicalUrl":"https://agenova.io/agents/zed-agent","updatedAt":"2026-09-09T21:54:18.666Z","category":{"name":"Coding agents","slug":"coding"},"purposeCategory":null,"status":"active"},"summary":"Zed Agent is the native agent path inside the Zed editor for reading and editing projects, running terminal commands, and using configured tools.","identity":{"state":"source_backed","lastVerifiedAt":"2026-09-09"},"facts":[{"field":"pricing","value":"CONDITIONAL — official first-party source: Zed's official plans document free use with configured API keys and paid Pro access to hosted models.","state":"source_backed","evidenceState":"source_backed","gap":null,"observedAt":"2026-09-09T21:54:18.666Z","validUntil":"2026-10-09T21:54:18.666Z","assertionState":"conditional","scope":"official first-party source","normalizedValue":"Zed's official plans document free use with configured API keys and paid Pro access to hosted models.","sources":[{"id":"src_sv491_b44_zed_agent_pricing","title":"Zed Agent official pricing page source","publisher":"Zed Agent","url":"https://zed.dev/docs/account/plans-and-pricing"}]},{"field":"capabilities","value":"YES — agent tool execution: Can configure Agent Panel tools to run automatically or require approval, with rules for trusted, blocked, and sensitive actions.","state":"source_backed","evidenceState":"source_backed","gap":null,"observedAt":"2026-09-06T19:31:18.600Z","validUntil":"2027-03-05T19:31:18.658Z","assertionState":"yes","scope":"agent tool execution","normalizedValue":"Can configure Agent Panel tools to run automatically or require approval, with rules for trusted, blocked, and sensitive actions.","sources":[{"id":"phase3-src-a807adb6bba0d5de6b564a266200257d","title":"Zed Agent official integrations source","publisher":"Zed Agent","url":"https://zed.dev/docs/ai/tool-permissions"}]},{"field":"deployment","value":"YES — model execution: Supports locally run or self-hosted language models.","state":"source_backed","evidenceState":"source_backed","gap":null,"observedAt":"2026-09-06T19:28:36.364Z","validUntil":"2027-03-05T19:28:36.420Z","assertionState":"yes","scope":"model execution","normalizedValue":"Supports locally run or self-hosted language models.","sources":[{"id":"phase3-src-9eafb2493ae2d25202e3688c498c7fd4","title":"Zed Agent official integrations source","publisher":"Zed Agent","url":"https://zed.dev/docs/ai/llm-providers"}]},{"field":"enterpriseControls","value":"YES — tool policy controls: Supports allow, deny, and confirmation policies at global and tool-specific levels using matched command, path, or URL patterns.","state":"source_backed","evidenceState":"source_backed","gap":null,"observedAt":"2026-09-06T19:31:18.747Z","validUntil":"2027-03-05T19:31:18.805Z","assertionState":"yes","scope":"tool policy controls","normalizedValue":"Supports allow, deny, and confirmation policies at global and tool-specific levels using matched command, path, or URL patterns.","sources":[{"id":"phase3-src-a807adb6bba0d5de6b564a266200257d","title":"Zed Agent official integrations source","publisher":"Zed Agent","url":"https://zed.dev/docs/ai/tool-permissions"}]},{"field":"privacyDataPolicy","value":"CONDITIONAL — AI code and prompt data: Discards code and prompts after each request and does not use them for AI training, except that designated provider models may retain data briefly for safety.","state":"source_backed","evidenceState":"source_backed","gap":null,"observedAt":"2026-09-06T19:32:20.419Z","validUntil":"2027-03-05T19:32:20.479Z","assertionState":"conditional","scope":"AI code and prompt data","normalizedValue":"Discards code and prompts after each request and does not use them for AI training, except that designated provider models may retain data briefly for safety.","sources":[{"id":"phase3-src-0995af9e26a2c8c5662590223623a87c","title":"Zed Agent official privacyDataPolicy source","publisher":"Zed Agent","url":"https://zed.dev/privacy"}]},{"field":"integrations","value":"YES — MCP tool integrations: Can apply per-tool permissions to MCP integrations using server and tool names, including GitHub issue and pull-request tools.","state":"source_backed","evidenceState":"source_backed","gap":null,"observedAt":"2026-09-06T19:31:18.893Z","validUntil":"2027-03-05T19:31:18.949Z","assertionState":"yes","scope":"MCP tool integrations","normalizedValue":"Can apply per-tool permissions to MCP integrations using server and tool names, including GitHub issue and pull-request tools.","sources":[{"id":"phase3-src-a807adb6bba0d5de6b564a266200257d","title":"Zed Agent official integrations source","publisher":"Zed Agent","url":"https://zed.dev/docs/ai/tool-permissions"}]},{"field":"regionalAvailability","value":"No directly supporting official source has passed field-level review.","state":"unknown","evidenceState":"unknown","gap":"intelligence","observedAt":"2026-09-09","validUntil":"2026-10-09T00:00:00.000Z","assertionState":"unknown","scope":"named market eligibility; reachability alone is not support","normalizedValue":null,"sources":[]},{"field":"executionReliability","value":"No publication-approved execution evidence is available for this Agent.","state":"unknown","evidenceState":"unknown","gap":"execution_evidence","observedAt":"2026-09-09","validUntil":"2026-10-09T00:00:00.000Z","assertionState":"unknown","scope":"condition-scoped Agenova execution evidence","normalizedValue":null,"sources":[]}],"evidenceCoverage":{"reliable":6,"sourceBacked":6,"executionVerified":0,"unverified":2,"total":8,"coverage":0.75},"provenance":{"policy":"official-source facts remain attributable; absent vendor statements are not negative claims","generatedFrom":"the same published Fact and accepted Evidence reader used by the public Agent profile"}}