{ "data": { "similar": [ { "grade": "BB", "json": "https://www.anchorterminal.com/tools/goose.json", "name": "goose", "score": 71.3, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "goose" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/axlr.json", "name": "AXLR", "score": 70.6, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "axlr" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/openhands.json", "name": "OpenHands", "score": 70.3, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "openhands" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/opencode.json", "name": "OpenCode", "score": 68.8, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "opencode" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/qwen-code.json", "name": "Qwen Code", "score": 68.7, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "qwen-code" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/kilo-code-cli.json", "name": "Kilo Code CLI", "score": 68, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "kilo-code-cli" } ], "tool": { "slug": "letta", "name": "Letta", "vendor": "Letta", "vendorUrl": "https://www.letta.com", "kind": "harness", "category": "agent-harnesses", "summary": "Letta, from the MemGPT team, is an open-source agent harness (formerly Letta Code) for stateful agents that keep memory blocks, skills and conversations across sessions, used from a CLI, chat.letta.com, messaging channels or the Agent SDK, with Letta Cloud.", "url": "https://www.anchorterminal.com/tools/letta", "markdownUrl": "https://www.anchorterminal.com/tools/letta.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/letta.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/letta.json", "dns": "letta.grade.anchorterminal.com", "repo": "https://github.com/letta-ai/letta-code", "license": "Apache-2.0", "transports": [ "stdio" ], "packages": [ { "registry": "npm", "name": "@letta-ai/letta-code" }, { "registry": "pypi", "name": "letta" } ], "auth": "mixed", "authNotes": "Local use needs only the user's own model keys or coding-plan logins through `/connect`. Signing in with Letta (`/login`, OAuth in the browser) stores agents in Letta Cloud and enables remote computers and secrets. Developer plans use Letta API keys.", "pricing": "freemium", "pricingNotes": "Free plan at $0 with bring-your-own keys and limited agents and storage. Pro $20 a month with Letta Auto quotas and up to 20 agents. API plan $20 a month plus $0.10 per active agent a month and $0.00015 a second of tool execution, with LLM usage at token cost.", "priceSummary": "$20 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the letta-code source, docs.letta.com's llms.txt or the pricing page (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 3793, "npmWeekly": 85863, "pypiWeekly": 2225, "asOf": "2026-11-06" }, "docsUrl": "https://docs.letta.com", "llmsTxt": "https://docs.letta.com/llms.txt", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent", "memory.store", "memory.search" ], "tags": [ "open-source", "local", "hosted", "freemium", "apache-2.0", "typescript", "cli", "headless", "telemetry", "llms-txt", "memory" ], "lastRelease": "2026-11-06", "graded": true, "anchor": { "graded": true, "score": 59.7, "grade": "C", "agentReady": false, "rank": 684, "ranked": true, "rankOf": 1486, "categoryRank": 18, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 85, "payments": 60, "reliability": 58, "schema": 70, "security": 35, "transparency": 55 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 58, "points": 11.6, "reason": "Local-software lines, read for the harness. `@letta-ai/letta-code` on npm with Node.js 22.19 or newer, and PyPI wheels for glibc Linux, macOS 14 and Windows x64 with Python 3.9 or newer stated (20). ci.yml, nightly update smoke tests and Telegram live smoke tests exist, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 332 open issues and pull requests, mostly pull requests; recent bug reports such as recall reading the wrong conversation have no reply yet (15 of 25). 398 tags at 0.34.x with release notes on GitHub, no changelog file, and breaking removals such as AgentFile announced in the README (8 of 15). Pre-1.0 (0). Total 58.", "checked": "2026-11-06" }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 70, "points": 11.38, "reason": "Harness reading. docs.letta.com serves llms.txt and a Markdown version of every page, with an `applies_to` block saying which backend and interface each page covers (10). TypeScript types for the Agent SDK and a documented App Server WebSocket protocol, but no JSON Schema or OpenAPI for the harness (15 of 25). Pages say when to use local or cloud backends, subagents and channels (14 of 20). Permission modes and options are typed in the SDK (12 of 15). Example applications and a remote client reference (11 of 15). Releases most days but no changelog file (8 of 15). Total 70.", "checked": "2026-11-06" }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 67, "points": 10.89, "reason": "Harness reading. Toolsets switch with `/model`, skills load per agent, and subagents run in the background (18 of 25). Context is managed through memory blocks, reflection and dreaming (12 of 20). `letta -p --output-format json` for scripted runs and an App Server for programmatic control (12 of 20). Conversations resume by agent and conversation id, and memory is git-tracked so changes can be reverted (15 of 20). Runs with no account on the local backend, with one SDK language, TypeScript (10 of 15). Total 67.", "checked": "2026-11-06" }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 35, "points": 6.13, "reason": "Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for injection posture, 15 for audit and 20 for the security programme. Letta Cloud is the default backend, so agent state and conversations go to Letta's servers, and telemetry is on by default (10 of 30). The default permission mode is `unrestricted`; `standard`, `acceptEdits` and `strict` are opt-in, and cloud sandboxes exist for remote work (4 of 20). No prompt-injection guidance found for fetched pages or channel messages (5 of 15). Conversation search and git history of memory give an operator a record of what the agent saw and changed (10 of 15). SECURITY.md routes reports to support@letta.com and scopes out the retired server; no security.txt, bounty or certification found (6 of 20). Total 35.", "checked": "2026-11-06" }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 60, "points": 7.5, "reason": "No x402, MPP or L402 (0 of 40). Per-unit API prices are public, $0.10 per active agent a month and $0.00015 a second of tool execution, plus plan prices (20). A $0 plan with bring-your-own keys; no card is mentioned (20). The CLI runs locally without signing in (20). Total 60.", "checked": "2026-11-06" }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 85, "points": 7.44, "reason": "v0.34.42 on 6 November 2026 (30). Dozens of releases in 90 days (20). Pull requests are merged daily; recent issues from users have few replies (15 of 25). npm and PyPI packages and the Agent SDK track the releases (12 of 15). Lock files, CI and nightly smoke tests (8 of 10). Total 85.", "checked": "2026-11-06" }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 55, "points": 4.81, "note": "editorial 55, provenance 54", "reason": "Apache-2.0 (30). The privacy policy has no date, no legal entity and no retention periods, and says hosted message data may train future models (8 of 30). The README and docs mark AgentFile, the Electron app and the V1 server as deprecated or retired, without dated notice periods (12 of 20). Telemetry is described in the privacy policy only as basic and opt-out when supported; the LETTA_CODE_TELEM=0 switch appears only in the source (5 of 20). Total 55.", "checked": "2026-11-06" } ], "assessment": { "date": "2026-11-06", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Harness reading. Toolsets switch with `/model`, skills load per agent, and subagents run in the background (18 of 25). Context is managed through memory blocks, reflection and dreaming (12 of 20). `letta -p --output-format json` for scripted runs and an App Server for programmatic control (12 of 20). Conversations resume by agent and conversation id, and memory is git-tracked so changes can be reverted (15 of 20). Runs with no account on the local backend, with one SDK language, TypeScript (10 of 15). Total 67.", "maintenance": "v0.34.42 on 6 November 2026 (30). Dozens of releases in 90 days (20). Pull requests are merged daily; recent issues from users have few replies (15 of 25). npm and PyPI packages and the Agent SDK track the releases (12 of 15). Lock files, CI and nightly smoke tests (8 of 10). Total 85.", "payments": "No x402, MPP or L402 (0 of 40). Per-unit API prices are public, $0.10 per active agent a month and $0.00015 a second of tool execution, plus plan prices (20). A $0 plan with bring-your-own keys; no card is mentioned (20). The CLI runs locally without signing in (20). Total 60.", "reliability": "Local-software lines, read for the harness. `@letta-ai/letta-code` on npm with Node.js 22.19 or newer, and PyPI wheels for glibc Linux, macOS 14 and Windows x64 with Python 3.9 or newer stated (20). ci.yml, nightly update smoke tests and Telegram live smoke tests exist, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 332 open issues and pull requests, mostly pull requests; recent bug reports such as recall reading the wrong conversation have no reply yet (15 of 25). 398 tags at 0.34.x with release notes on GitHub, no changelog file, and breaking removals such as AgentFile announced in the README (8 of 15). Pre-1.0 (0). Total 58.", "schema": "Harness reading. docs.letta.com serves llms.txt and a Markdown version of every page, with an `applies_to` block saying which backend and interface each page covers (10). TypeScript types for the Agent SDK and a documented App Server WebSocket protocol, but no JSON Schema or OpenAPI for the harness (15 of 25). Pages say when to use local or cloud backends, subagents and channels (14 of 20). Permission modes and options are typed in the SDK (12 of 15). Example applications and a remote client reference (11 of 15). Releases most days but no changelog file (8 of 15). Total 70.", "security": "Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for injection posture, 15 for audit and 20 for the security programme. Letta Cloud is the default backend, so agent state and conversations go to Letta's servers, and telemetry is on by default (10 of 30). The default permission mode is `unrestricted`; `standard`, `acceptEdits` and `strict` are opt-in, and cloud sandboxes exist for remote work (4 of 20). No prompt-injection guidance found for fetched pages or channel messages (5 of 15). Conversation search and git history of memory give an operator a record of what the agent saw and changed (10 of 15). SECURITY.md routes reports to support@letta.com and scopes out the retired server; no security.txt, bounty or certification found (6 of 20). Total 35.", "transparency": "Apache-2.0 (30). The privacy policy has no date, no legal entity and no retention periods, and says hosted message data may train future models (8 of 30). The README and docs mark AgentFile, the Electron app and the V1 server as deprecated or retired, without dated notice periods (12 of 20). Telemetry is described in the privacy policy only as basic and opt-out when supported; the LETTA_CODE_TELEM=0 switch appears only in the source (5 of 20). Total 55." }, "sources": [ { "what": "letta-code repository, README and source (clone)", "url": "https://github.com/letta-ai/letta-code", "seen": "2026-11-06" }, { "what": "permission modes source", "url": "https://github.com/letta-ai/letta-code/blob/main/src/permissions/mode.ts", "seen": "2026-11-06" }, { "what": "letta landing repository README and SECURITY.md", "url": "https://github.com/letta-ai/letta", "seen": "2026-11-06" }, { "what": "docs llms.txt", "url": "https://docs.letta.com/llms.txt", "seen": "2026-11-06" }, { "what": "pricing", "url": "https://docs.letta.com/pricing/index.md", "seen": "2026-11-06" }, { "what": "privacy policy", "url": "https://www.letta.com/privacy-policy", "seen": "2026-11-06" }, { "what": "npm downloads", "url": "https://api.npmjs.org/downloads/point/last-week/@letta-ai/letta-code", "seen": "2026-11-06" }, { "what": "seed round release (24 September 2024)", "url": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "seen": "2026-11-06" } ], "openQuestions": [ "The lead described Letta as the Letta Agent SDK, CLI, MCP, Letta Cloud or a self-hosted App Server. That holds, but the Letta V1 API server that most memory comparisons describe is retired, so the listing is graded as a harness in agent-harnesses with agent-memory as a second category.", "unchecked: CI run results, because GitHub's API answered with a rate limit.", "unchecked: the terms of service, left to the policy reader at landing.", "Whether the V1 server's retirement came with advance notice wasn't established; no deduction is taken without it.", "Lapse. pypi.org/pypi/\u003cpackage\u003e/json, which PyPI's robots.txt disallows (/pypi/*/json), was fetched for this listing's packages on 6 November 2026 before robots.txt was read. Nothing from those responses is used; versions and release dates come from the allowed release feed at pypi.org/rss/project/\u003cpackage\u003e/releases.xml, and licences and authors from the repository.", "firstReleased is letta-code's first tag, v0.1.3 on 24 October 2025. The `letta` name on PyPI and the MemGPT repository are older, from the V1 server." ] }, "negative": 0, "verdict": "Letta's open-source harness gives agents git-tracked memory blocks, skills, subagents and headless JSON runs, with a $0 plan and public per-agent API prices. It starts in the unrestricted permission mode, defaults to Letta Cloud, sends usage telemetry unless LETTA_CODE_TELEM=0 is set, and the V1 API server the comparisons describe is retired.", "bestFor": "Long-lived coding agents and assistants that keep memory and identity across sessions and machines.", "strengths": [ "Apache-2.0 harness on npm and PyPI with 0.34.42 released on 6 November 2026, and releases most days", "Memory blocks and MemFS keep an agent's context in git, with optional sync to the user's own repository", "Headless runs with `-p` and `--output-format json`, plus a TypeScript Agent SDK and a self-hosted App Server", "Public prices, a $0 plan with bring-your-own keys, and an API plan at $20 a month plus $0.10 per active agent", "Runs locally without signing in, with `letta backend local` or `--backend local`" ], "weaknesses": [ "The default permission mode is `unrestricted`, the renamed `bypassPermissions`, so tool calls aren't confirmed unless the user picks another mode", "Letta Cloud is the default backend, so agent memory and conversations go to Letta's servers unless the user chooses local", "Usage telemetry is on by default, with the LETTA_CODE_TELEM=0 opt-out found only in the source", "The Letta V1 Python API server is retired and unsupported, and the letta-ai/letta repository is now a landing page", "The privacy policy names no legal entity or date and says hosted message data may train future models" ], "agentNotes": [ "Start headless runs with an explicit permission mode such as `standard` or `strict`; the default auto-approves tools", "Pass `--backend local` for work that must stay on the machine, since Letta Cloud is the default", "Set LETTA_CODE_TELEM=0 in unattended runs if usage events must not be sent", "Use `letta -p --output-format json` for scripted runs and parse the JSON, not the terminal output", "Don't plan on the retired V1 REST server or `.af` AgentFile import; both are gone" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.7 } ], "editorialScores": { "ergonomics": 67, "maintenance": 85, "payments": 60, "reliability": 58, "schema": 70, "security": 35, "transparency": 55 }, "provenanceScore": 54, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 }, "scoreHistory": [ { "date": "2026-11-06", "grade": "C", "kind": "listed", "method": "0.7", "score": 59.7 } ] }, "connect": { "install": "npm install -g @letta-ai/letta-code", "headless": { "local": "letta --backend local", "run": "letta -p --output-format json \"\u003ctask\u003e\"", "server": "letta server" } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/letta" }, "alsoIn": [ "agent-memory" ], "notable": [ "The letta-ai/letta repository is now a landing page. Its README says the current source lives in letta-ai/letta-code and that the retired Letta V1 API server is kept on an archive branch, and its SECURITY.md says that server receives no fixes or security updates (https://github.com/letta-ai/letta)", "DEFAULT_PERMISSION_MODE is `unrestricted` in src/permissions/mode.ts, which migrates the older `bypassPermissions` and `fullAccess` values to it (https://github.com/letta-ai/letta-code/blob/main/src/permissions/mode.ts)", "src/index.ts initialises telemetry with the comment \"enabled by default, opt-out via LETTA_CODE_TELEM=0\" (https://github.com/letta-ai/letta-code/blob/main/src/index.ts)", "The README says Letta Cloud is the default backend, chosen at first launch, and AgentFile (.af) export and import have been removed (https://github.com/letta-ai/letta-code/blob/main/README.md)", "v0.34.42 tagged on 6 November 2026; 398 tags in the repository, which was created on 25 October 2025 (https://github.com/letta-ai/letta-code)", "Letta's seed round of $10 million, led by Felicis, was announced on 24 September 2024 (https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html)" ], "area": "frameworks", "details": [ { "label": "Surface listed", "value": "The open-source Letta harness, `@letta-ai/letta-code` 0.34.42, with its CLI, headless mode and Agent SDK, read from clones of github.com/letta-ai/letta-code and letta-ai/letta, npm, PyPI, docs.letta.com's llms.txt and pricing page and letta.com's privacy policy on 6 November 2026. Nothing was installed or run" }, { "label": "Category", "value": "Agent harnesses, because Letta is now a finished program that runs the agent loop; memory is its distinguishing feature, so it also appears in agent memory" }, { "label": "Retired", "value": "The Letta V1 Python API server (letta-ai/letta, archive branch), its Docker images, the Electron desktop app and AgentFile import and export" }, { "label": "Interfaces", "value": "CLI and terminal UI, chat.letta.com in the browser, Slack, Telegram, Discord and custom channels, the TypeScript Agent SDK, the Letta App Server over WebSocket, and ACP" }, { "label": "Legal entity", "value": "Not named in the privacy policy, which says only Letta. The company announced itself as Letta, of San Francisco, in its September 2024 release" } ], "unitPrices": [ { "item": "Pro plan", "unit": "month", "usd": 20, "note": "Letta Auto quotas, up to 20 agents" }, { "item": "API plan active agent", "unit": "month", "usd": 0.1, "note": "Plus $20 a month base and $0.00015 a second of tool execution" } ], "provenance": { "legalEntity": "", "domain": "letta.com", "domainRegistered": "1997-10-01", "endpointOnVendorDomain": null, "terms": "https://www.letta.com/terms-of-service", "privacy": "https://www.letta.com/privacy-policy", "statusPage": "", "changelog": "https://github.com/letta-ai/letta-code/releases", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The privacy policy shows no last-updated date and names no legal entity, only Letta. It says hosted message data may be used to train new models and that basic telemetry can be turned off in settings when supported.", "www.letta.com and docs.letta.com robots.txt allow all crawlers.", "RDAP gives letta.com a registration date of 1 October 1997, which predates the company, so the domain was bought later.", "/.well-known/security.txt returns 404. SECURITY.md in letta-ai/letta asks for reports to support@letta.com.", "The terms URL is the conventional path and was not read; the policy reader checks it at landing." ], "score": 54, "checks": [ { "check": "Legal entity named", "value": "not found", "points": 0, "max": 20, "state": "no" }, { "check": "Domain age", "value": "letta.com, registered 1997-10-01 (29 years)", "points": 15, "max": 15, "state": "ok" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "read, states 5 of the 7 things a reader expects", "points": 8.3, "max": 10, "state": "part" }, { "check": "Privacy policy", "value": "read, states 6 of the 8 things a reader expects", "points": 8.5, "max": 10, "state": "part" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "People named", "value": "2 named with their role, none with a public profile", "points": 7, "max": 10, "state": "part" }, { "check": "Support route", "value": "a support address, help pages, a community", "points": 5, "max": 5, "state": "ok" } ], "policies": [ { "kind": "terms", "url": "https://www.letta.com/terms-of-service", "state": "read", "readAt": "2026-11-06", "words": 1060, "points": 8.3, "max": 10, "expected": [ { "key": "terms.date", "label": "Gives the date it was last updated", "found": false }, { "key": "terms.law", "label": "Names the governing law or courts", "found": true, "quote": "These Terms and your use of the Services are governed by the laws of the State of California, United States of America, without regard to its conflict-of-law principles.", "says": "The law of the State of California" }, { "key": "terms.liability", "label": "States a limit on its liability", "found": true, "quote": "As a condition of accessing the Services, you understand and agree that Letta's total liability will not exceed $4.20.", "says": "Capped at $4.20" }, { "key": "terms.termination", "label": "Says how the agreement or account can be ended", "found": true, "quote": "We may suspend or terminate the Services at any time, at our discretion and without notice." }, { "key": "terms.changes", "label": "Says how changes to the terms are announced", "found": true, "quote": "The notice will specify a reasonable period after which the updated Terms take effect.", "says": "Says it gives notice of a change" }, { "key": "terms.use", "label": "Lists what users may not do", "found": true, "quote": "If you do not agree to these Terms, you may not use the Services." }, { "key": "terms.sla", "label": "Refers to a service level or uptime commitment", "found": false } ], "toKnow": [ { "key": "terms.cutoff", "label": "Says access can be ended without notice or for any reason", "found": true, "quote": "We may suspend or terminate the Services at any time, at our discretion and without notice." }, { "key": "terms.arbitration", "label": "Requires arbitration or waives class actions", "found": true, "quote": "Any dispute that arose before the changes will be governed by the Terms (including the binding individual arbitration clause) in effect when the dispute arose." } ] }, { "kind": "privacy", "url": "https://www.letta.com/privacy-policy", "state": "read", "readAt": "2026-11-06", "words": 3460, "points": 8.5, "max": 10, "expected": [ { "key": "privacy.date", "label": "Gives the date it was last updated", "found": false }, { "key": "privacy.collected", "label": "Says what personal data is collected", "found": true, "quote": "When you use Letta applications/services/websites, we collect basic telemetry data such as clicks, crashes, etc." }, { "key": "privacy.retention", "label": "Says how long data is kept", "found": true, "quote": "We retain this information for the length of time described in our \"How Long We Keep Information section\"." }, { "key": "privacy.processors", "label": "Says who else receives the data", "found": true, "quote": "Third-party vendors: We may share information about you with third-party vendors who need the information in order to provide their services to us, or to provide their services to you or your site." }, { "key": "privacy.sale", "label": "Says whether personal data is sold or shared for advertising", "found": true, "quote": "Opt out of the sale or sharing of personal information;" }, { "key": "privacy.rights", "label": "Says what rights people have over their data", "found": true, "quote": "If you are located in certain parts of the world, including some US states and countries that fall under the scope of the European General Data Protection Regulation (aka the \"GDPR\"), you may have certain rights regarding your personal information, like the right to request access to or deletion of your data." }, { "key": "privacy.contact", "label": "Gives a privacy contact", "found": true, "quote": "If you have a question about this Privacy Policy, please contact us through our via email." }, { "key": "privacy.transfers", "label": "Says where data is transferred or stored", "found": false } ] } ] }, "humans": { "slug": "letta", "checked": "2026-11-06", "company": "Letta", "people": [ { "name": "Charles Packer", "role": "Co-founder and CEO", "founder": true, "page": "/people/charles-packer/" }, { "name": "Sarah Wooders", "role": "Co-founder and CTO", "founder": true, "page": "/people/sarah-wooders/" } ], "peopleNote": "Roles from Letta's own release of 24 September 2024 on PR Newswire (\"SOURCE Letta\"), which names Charles Packer and Sarah Wooders as co-founders and quotes them as CEO and CTO. letta.com has no about or team page (404 on /about, /company and /team on 6 November 2026). Personal profiles weren't linked from a first-hand page, so none are given. The release names seven angels, listed here with its words. letta.com's sitemap, its announcement post of 23 September 2024 and a web search on 6 November 2026 found no round after the $10 million seed, so the total raised is that seed. No valuation has been stated.", "companySocial": { "github": "https://github.com/letta-ai" }, "support": { "emails": [ "support@letta.com" ], "urls": [ "https://docs.letta.com", "https://github.com/letta-ai/letta-code/issues" ], "community": [ { "label": "Discord", "url": "https://discord.gg/letta", "kind": "discord" } ] }, "sources": [ "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "https://github.com/letta-ai/letta/blob/main/SECURITY.md", "https://github.com/letta-ai/letta-code" ], "ownership": { "status": "private", "totalRaised": { "amount": "$10M", "asOf": "2024-09", "source": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html" }, "checked": "2026-11-06", "sources": [ "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html" ] }, "investors": [ { "name": "Felicis", "kind": "vc", "rounds": [ "Seed, September 2024" ], "lead": true, "url": "https://www.felicis.com", "source": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "quote": "Letta \"emerged from stealth today with a $10 million seed round led by Felicis with participation from Sunflower Capital and Essence VC.\"", "page": "/investors/felicis/" }, { "name": "Sunflower Capital", "kind": "vc", "rounds": [ "Seed, September 2024" ], "url": "https://sunflowercapital.co", "source": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "quote": "Letta \"emerged from stealth today with a $10 million seed round led by Felicis with participation from Sunflower Capital and Essence VC.\"", "page": "/investors/sunflower-capital/" }, { "name": "Essence VC", "kind": "vc", "rounds": [ "Seed, September 2024" ], "url": "https://www.essencevc.fund", "source": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "quote": "Letta \"emerged from stealth today with a $10 million seed round led by Felicis with participation from Sunflower Capital and Essence VC.\"", "page": "/investors/essence-vc/" }, { "name": "Jeff Dean", "kind": "angel", "rounds": [ "Seed, September 2024" ], "source": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "quote": "Notable angels include Jeff Dean (Chief Scientist at Google DeepMind), Clem Delangue (CEO of HuggingFace), Cristobal Valenzuela (CEO of Runway), Jordan Tigani (CEO of MotherDuck), Tristan Handy (CEO of dbt Labs), Robert Nishihara (co-founder of Anyscale), and Barry McCardel (CEO of Hex).", "page": "/investors/jeff-dean/" }, { "name": "Clem Delangue", "kind": "angel", "rounds": [ "Seed, September 2024" ], "source": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "quote": "Notable angels include Jeff Dean (Chief Scientist at Google DeepMind), Clem Delangue (CEO of HuggingFace), Cristobal Valenzuela (CEO of Runway), Jordan Tigani (CEO of MotherDuck), Tristan Handy (CEO of dbt Labs), Robert Nishihara (co-founder of Anyscale), and Barry McCardel (CEO of Hex).", "page": "/investors/clem-delangue/" }, { "name": "Cristobal Valenzuela", "kind": "angel", "rounds": [ "Seed, September 2024" ], "source": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "quote": "Notable angels include Jeff Dean (Chief Scientist at Google DeepMind), Clem Delangue (CEO of HuggingFace), Cristobal Valenzuela (CEO of Runway), Jordan Tigani (CEO of MotherDuck), Tristan Handy (CEO of dbt Labs), Robert Nishihara (co-founder of Anyscale), and Barry McCardel (CEO of Hex).", "page": "/investors/cristobal-valenzuela/" }, { "name": "Jordan Tigani", "kind": "angel", "rounds": [ "Seed, September 2024" ], "source": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "quote": "Notable angels include Jeff Dean (Chief Scientist at Google DeepMind), Clem Delangue (CEO of HuggingFace), Cristobal Valenzuela (CEO of Runway), Jordan Tigani (CEO of MotherDuck), Tristan Handy (CEO of dbt Labs), Robert Nishihara (co-founder of Anyscale), and Barry McCardel (CEO of Hex).", "page": "/investors/jordan-tigani/" }, { "name": "Tristan Handy", "kind": "angel", "rounds": [ "Seed, September 2024" ], "source": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "quote": "Notable angels include Jeff Dean (Chief Scientist at Google DeepMind), Clem Delangue (CEO of HuggingFace), Cristobal Valenzuela (CEO of Runway), Jordan Tigani (CEO of MotherDuck), Tristan Handy (CEO of dbt Labs), Robert Nishihara (co-founder of Anyscale), and Barry McCardel (CEO of Hex).", "page": "/investors/tristan-handy/" }, { "name": "Robert Nishihara", "kind": "angel", "rounds": [ "Seed, September 2024" ], "source": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "quote": "Notable angels include Jeff Dean (Chief Scientist at Google DeepMind), Clem Delangue (CEO of HuggingFace), Cristobal Valenzuela (CEO of Runway), Jordan Tigani (CEO of MotherDuck), Tristan Handy (CEO of dbt Labs), Robert Nishihara (co-founder of Anyscale), and Barry McCardel (CEO of Hex).", "page": "/investors/robert-nishihara/" }, { "name": "Barry McCardel", "kind": "angel", "rounds": [ "Seed, September 2024" ], "source": "https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html", "quote": "Notable angels include Jeff Dean (Chief Scientist at Google DeepMind), Clem Delangue (CEO of HuggingFace), Cristobal Valenzuela (CEO of Runway), Jordan Tigani (CEO of MotherDuck), Tristan Handy (CEO of dbt Labs), Robert Nishihara (co-founder of Anyscale), and Barry McCardel (CEO of Hex).", "page": "/investors/barry-mccardel/" } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/letta.json", "live": { "slug": "letta", "versions": [ { "registry": "github", "name": "letta-ai/letta-code", "version": "v0.34.43", "released": "2026-11-06", "seenAt": "2026-11-06T23:39:39.434291816Z" }, { "registry": "npm", "name": "@letta-ai/letta-code", "version": "0.34.43", "seenAt": "2026-11-06T23:39:38.413416142Z" }, { "registry": "pypi", "name": "letta", "version": "0.34.12", "released": "2026-10-12", "seenAt": "2026-11-06T23:39:39.241816797Z" } ], "githubStars": 3794, "npmWeekly": 85863, "pypiWeekly": 2225, "securityTxt": { "url": "https://letta.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:02.768002207Z" }, "llmsTxt": { "url": "https://docs.letta.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:52.28674296Z" }, "pages": [ { "url": "https://www.letta.com/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:30:46.549817082Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "947a68f3e3a0" }, { "url": "https://www.letta.com/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:30:48.740250784Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "63f31d6ebfb8" } ], "updatedAt": "2026-11-07T16:01:02.768002207Z" } }, "verify": { "accepts": "a page on letta.com or one of its subdomains, or the README at the root of github.com/letta-ai/letta-code", "badgeUrl": "https://www.anchorterminal.com/badges/letta.svg", "body": { "slug": "letta", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/letta", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/letta\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/letta.svg\" alt=\"Letta on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![Letta on Anchor Terminal](https://www.anchorterminal.com/badges/letta.svg)](https://www.anchorterminal.com/tools/letta)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/letta\"\u003eLetta on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/letta", "json": "https://www.anchorterminal.com/tools/letta.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/letta.md", "mcp": "https://www.anchorterminal.com/mcp", "pricing": "https://www.anchorterminal.com/tools/letta#pricing", "reviews": "https://www.anchorterminal.com/tools/letta#reviews", "slim": "https://www.anchorterminal.com/tools/letta.min.md" }, "markdown": "## Overview\n\n**Grade C · 59.7/100 · rank #684 of 1486 · #18 in Agent harnesses · not agent-ready · confidence medium**\n\n\nAlso listed in [Agent memory](https://www.anchorterminal.com/categories/agent-memory.md).\n\n## Assessment\n\nLetta's open-source harness gives agents git-tracked memory blocks, skills, subagents and headless JSON runs, with a $0 plan and public per-agent API prices. It starts in the unrestricted permission mode, defaults to Letta Cloud, sends usage telemetry unless LETTA_CODE_TELEM=0 is set, and the V1 API server the comparisons describe is retired.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | Letta (https://www.letta.com) |\n| Kind | Agent harness |\n| Category | Agent harnesses (https://www.anchorterminal.com/categories/agent-harnesses) |\n| Transport | stdio |\n| Auth | OAuth or key · Local use needs only the user's own model keys or coding-plan logins through `/connect`. Signing in with Letta (`/login`, OAuth in the browser) stores agents in Letta Cloud and enables remote computers and secrets. Developer plans use Letta API keys. |\n| Pricing | Freemium ($20 / mo) · Free plan at $0 with bring-your-own keys and limited agents and storage. Pro $20 a month with Letta Auto quotas and up to 20 agents. API plan $20 a month plus $0.10 per active agent a month and $0.00015 a second of tool execution, with LLM usage at token cost. |\n| x402 | No · No x402, MPP or L402 in the letta-code source, docs.letta.com's llms.txt or the pricing page (checked 2026-11-06). |\n| Licence | Apache-2.0 |\n| Packages | npm: `@letta-ai/letta-code`; pypi: `letta` |\n| Source | https://github.com/letta-ai/letta-code |\n| Docs | https://docs.letta.com |\n| llms.txt | https://docs.letta.com/llms.txt |\n| Last release | 2026-11-06 |\n| GitHub stars | 3,793 (as of 2026-11-06) |\n| npm downloads / week | 85,863 |\n| PyPI downloads / week | 2,225 |\n| Surface listed | The open-source Letta harness, `@letta-ai/letta-code` 0.34.42, with its CLI, headless mode and Agent SDK, read from clones of github.com/letta-ai/letta-code and letta-ai/letta, npm, PyPI, docs.letta.com's llms.txt and pricing page and letta.com's privacy policy on 6 November 2026. Nothing was installed or run |\n| Category | Agent harnesses, because Letta is now a finished program that runs the agent loop; memory is its distinguishing feature, so it also appears in agent memory |\n| Retired | The Letta V1 Python API server (letta-ai/letta, archive branch), its Docker images, the Electron desktop app and AgentFile import and export |\n| Interfaces | CLI and terminal UI, chat.letta.com in the browser, Slack, Telegram, Discord and custom channels, the TypeScript Agent SDK, the Letta App Server over WebSocket, and ACP |\n| Legal entity | Not named in the privacy policy, which says only Letta. The company announced itself as Letta, of San Francisco, in its September 2024 release |\n| Capabilities | agent.harness, agent.mcp-client, agent.multi-agent, memory.store, memory.search |\n| Tags | open-source, local, hosted, freemium, apache-2.0, typescript, cli, headless, telemetry, llms-txt, memory |\n| JSON | https://www.anchorterminal.com/api/v1/tools/letta.json |\n\n## Score breakdown (methodology v0.7, October 2026 research run)\n\nAssessed 2026-11-06 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 58 | 11.6 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 70 | 11.4 |\n| Agent ergonomics | 13% | 16.2 | 67 | 10.9 |\n| Security \u0026 auth | 14% | 17.5 | 35 | 6.1 |\n| Payments \u0026 pricing | 10% | 12.5 | 60 | 7.5 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 85 | 7.4 |\n| Transparency \u0026 trust (editorial 55, provenance 54) | 7% | 8.8 | 55 | 4.8 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **59.7 → C** |\n\n### Why each score\n\n- Reliability 58 (checked 2026-11-06): Local-software lines, read for the harness. `@letta-ai/letta-code` on npm with Node.js 22.19 or newer, and PyPI wheels for glibc Linux, macOS 14 and Windows x64 with Python 3.9 or newer stated (20). ci.yml, nightly update smoke tests and Telegram live smoke tests exist, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 332 open issues and pull requests, mostly pull requests; recent bug reports such as recall reading the wrong conversation have no reply yet (15 of 25). 398 tags at 0.34.x with release notes on GitHub, no changelog file, and breaking removals such as AgentFile announced in the README (8 of 15). Pre-1.0 (0). Total 58.\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 70 (checked 2026-11-06): Harness reading. docs.letta.com serves llms.txt and a Markdown version of every page, with an `applies_to` block saying which backend and interface each page covers (10). TypeScript types for the Agent SDK and a documented App Server WebSocket protocol, but no JSON Schema or OpenAPI for the harness (15 of 25). Pages say when to use local or cloud backends, subagents and channels (14 of 20). Permission modes and options are typed in the SDK (12 of 15). Example applications and a remote client reference (11 of 15). Releases most days but no changelog file (8 of 15). Total 70.\n- Agent ergonomics 67 (checked 2026-11-06): Harness reading. Toolsets switch with `/model`, skills load per agent, and subagents run in the background (18 of 25). Context is managed through memory blocks, reflection and dreaming (12 of 20). `letta -p --output-format json` for scripted runs and an App Server for programmatic control (12 of 20). Conversations resume by agent and conversation id, and memory is git-tracked so changes can be reverted (15 of 20). Runs with no account on the local backend, with one SDK language, TypeScript (10 of 15). Total 67.\n- Security \u0026 auth 35 (checked 2026-11-06): Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for injection posture, 15 for audit and 20 for the security programme. Letta Cloud is the default backend, so agent state and conversations go to Letta's servers, and telemetry is on by default (10 of 30). The default permission mode is `unrestricted`; `standard`, `acceptEdits` and `strict` are opt-in, and cloud sandboxes exist for remote work (4 of 20). No prompt-injection guidance found for fetched pages or channel messages (5 of 15). Conversation search and git history of memory give an operator a record of what the agent saw and changed (10 of 15). SECURITY.md routes reports to support@letta.com and scopes out the retired server; no security.txt, bounty or certification found (6 of 20). Total 35.\n- Payments \u0026 pricing 60 (checked 2026-11-06): No x402, MPP or L402 (0 of 40). Per-unit API prices are public, $0.10 per active agent a month and $0.00015 a second of tool execution, plus plan prices (20). A $0 plan with bring-your-own keys; no card is mentioned (20). The CLI runs locally without signing in (20). Total 60.\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 85 (checked 2026-11-06): v0.34.42 on 6 November 2026 (30). Dozens of releases in 90 days (20). Pull requests are merged daily; recent issues from users have few replies (15 of 25). npm and PyPI packages and the Agent SDK track the releases (12 of 15). Lock files, CI and nightly smoke tests (8 of 10). Total 85.\n- Transparency \u0026 trust 55 (checked 2026-11-06): Apache-2.0 (30). The privacy policy has no date, no legal entity and no retention periods, and says hosted message data may train future models (8 of 30). The README and docs mark AgentFile, the Electron app and the V1 server as deprecated or retired, without dated notice periods (12 of 20). Telemetry is described in the privacy policy only as basic and opt-out when supported; the LETTA_CODE_TELEM=0 switch appears only in the source (5 of 20). Total 55.\n\nFix list, everything this grade says the listing lacks, the biggest gain first (19 items). What it covers is at https://www.anchorterminal.com/fixes/letta.md (JSON https://www.anchorterminal.com/fixes/letta.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{\"listing\": \"letta\", \"plan\": \"read\"}`, free while the beta runs\n\n### What we couldn't check\n\n- The lead described Letta as the Letta Agent SDK, CLI, MCP, Letta Cloud or a self-hosted App Server. That holds, but the Letta V1 API server that most memory comparisons describe is retired, so the listing is graded as a harness in agent-harnesses with agent-memory as a second category.\n- unchecked: CI run results, because GitHub's API answered with a rate limit.\n- unchecked: the terms of service, left to the policy reader at landing.\n- Whether the V1 server's retirement came with advance notice wasn't established; no deduction is taken without it.\n- Lapse. pypi.org/pypi/\u003cpackage\u003e/json, which PyPI's robots.txt disallows (/pypi/*/json), was fetched for this listing's packages on 6 November 2026 before robots.txt was read. Nothing from those responses is used; versions and release dates come from the allowed release feed at pypi.org/rss/project/\u003cpackage\u003e/releases.xml, and licences and authors from the repository.\n- firstReleased is letta-code's first tag, v0.1.3 on 24 October 2025. The `letta` name on PyPI and the MemGPT repository are older, from the V1 server.\n\n### Sources\n\n- letta-code repository, README and source (clone): \u003chttps://github.com/letta-ai/letta-code\u003e (seen 2026-11-06)\n- permission modes source: \u003chttps://github.com/letta-ai/letta-code/blob/main/src/permissions/mode.ts\u003e (seen 2026-11-06)\n- letta landing repository README and SECURITY.md: \u003chttps://github.com/letta-ai/letta\u003e (seen 2026-11-06)\n- docs llms.txt: \u003chttps://docs.letta.com/llms.txt\u003e (seen 2026-11-06)\n- pricing: \u003chttps://docs.letta.com/pricing/index.md\u003e (seen 2026-11-06)\n- privacy policy: \u003chttps://www.letta.com/privacy-policy\u003e (seen 2026-11-06)\n- npm downloads: \u003chttps://api.npmjs.org/downloads/point/last-week/@letta-ai/letta-code\u003e (seen 2026-11-06)\n- seed round release (24 September 2024): \u003chttps://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html\u003e (seen 2026-11-06)\n\n## Score history\n\nEvery move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/letta/history.json\n\n- 2026-11-06: graded 59.7 C (methodology 0.7)\n\n## Who's behind it (provenance 54/100, checked 2026-11-06)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | not found | 0/20 |\n| Domain age | letta.com, registered 1997-10-01 (29 years) | 15/15 |\n| Endpoint on the vendor's domain | no hosted endpoint | n/a |\n| Terms of service | read, states 5 of the 7 things a reader expects | 8.3/10 |\n| Privacy policy | read, states 6 of the 8 things a reader expects | 8.5/10 |\n| Status page | not found | 0/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n| People named | 2 named with their role, none with a public profile | 7/10 |\n| Support route | a support address, help pages, a community | 5/5 |\n\nThe privacy policy shows no last-updated date and names no legal entity, only Letta. It says hosted message data may be used to train new models and that basic telemetry can be turned off in settings when supported.\n\nwww.letta.com and docs.letta.com robots.txt allow all crawlers.\n\nRDAP gives letta.com a registration date of 1 October 1997, which predates the company, so the domain was bought later.\n\n/.well-known/security.txt returns 404. SECURITY.md in letta-ai/letta asks for reports to support@letta.com.\n\nThe terms URL is the conventional path and was not read; the policy reader checks it at landing.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://www.letta.com/terms-of-service), read 2026-11-06, gives no date, states 5 of the 7 things a reader expects.\n\n- To know. Says access can be ended without notice or for any reason. \"We may suspend or terminate the Services at any time, at our discretion and without notice.\"\n- To know. Requires arbitration or waives class actions. \"Any dispute that arose before the changes will be governed by the Terms (including the binding individual arbitration clause) in effect when the dispute arose.\"\n- Not found in the text. Gives the date it was last updated.\n- Names the governing law or courts. The law of the State of California.\n- States a limit on its liability. Capped at $4.20.\n- Says how changes to the terms are announced. Says it gives notice of a change.\n- Not found in the text. Refers to a service level or uptime commitment.\n\n**Privacy policy** (https://www.letta.com/privacy-policy), read 2026-11-06, gives no date, states 6 of the 8 things a reader expects.\n\n- Not found in the text. Gives the date it was last updated.\n- Not found in the text. Says where data is transferred or stored.\n\n## Humans behind the project (researched 2026-11-06 from public pages, not part of the grade)\n\n### Key people\n\n- Charles Packer, Co-founder and CEO\n- Sarah Wooders, Co-founder and CTO\n- Note: Roles from Letta's own release of 24 September 2024 on PR Newswire (\"SOURCE Letta\"), which names Charles Packer and Sarah Wooders as co-founders and quotes them as CEO and CTO. letta.com has no about or team page (404 on /about, /company and /team on 6 November 2026). Personal profiles weren't linked from a first-hand page, so none are given. The release names seven angels, listed here with its words. letta.com's sitemap, its announcement post of 23 September 2024 and a web search on 6 November 2026 found no round after the $10 million seed, so the total raised is that seed. No valuation has been stated.\n- Letta: GitHub https://github.com/letta-ai\n\n### Ownership and investors\n\n- Raised: $10M in total, as of September 2024 (source https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html)\n- Backed by: Felicis, Sunflower Capital, Essence VC, Jeff Dean, Clem Delangue, Cristobal Valenzuela, Jordan Tigani, Tristan Handy, Robert Nishihara, Barry McCardel\n\n### Getting support\n\n- Discord: https://discord.gg/letta\n- Support email: support@letta.com\n- Help: https://docs.letta.com\n- Help: https://github.com/letta-ai/letta-code/issues\n- Sources: https://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html, https://github.com/letta-ai/letta/blob/main/SECURITY.md, https://github.com/letta-ai/letta-code\n\n## Live (updated 2026-11-07 16:01 UTC)\n\n- github `letta-ai/letta-code` v0.34.43, released 2026-11-06\n- npm `@letta-ai/letta-code` 0.34.43\n- pypi `letta` 0.34.12, released 2026-10-12\n- security.txt: none\n- Watching privacy \u003chttps://www.letta.com/privacy-policy\u003e\n- Watching terms \u003chttps://www.letta.com/terms-of-service\u003e\n- Always current: https://www.anchorterminal.com/api/v1/live/letta.json\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Prices\n\n| Item | Price | Unit | Note |\n| --- | --- | --- | --- |\n| Pro plan | $20 | per month (plan) | Letta Auto quotas, up to 20 agents |\n| API plan active agent | $0.10 | per month (plan) | Plus $20 a month base and $0.00015 a second of tool execution |\n\nAcross all listings: https://www.anchorterminal.com/prices/index.md\n\n## Strengths\n\n- Apache-2.0 harness on npm and PyPI with 0.34.42 released on 6 November 2026, and releases most days\n- Memory blocks and MemFS keep an agent's context in git, with optional sync to the user's own repository\n- Headless runs with `-p` and `--output-format json`, plus a TypeScript Agent SDK and a self-hosted App Server\n- Public prices, a $0 plan with bring-your-own keys, and an API plan at $20 a month plus $0.10 per active agent\n- Runs locally without signing in, with `letta backend local` or `--backend local`\n\n## Weaknesses\n\n- The default permission mode is `unrestricted`, the renamed `bypassPermissions`, so tool calls aren't confirmed unless the user picks another mode\n- Letta Cloud is the default backend, so agent memory and conversations go to Letta's servers unless the user chooses local\n- Usage telemetry is on by default, with the LETTA_CODE_TELEM=0 opt-out found only in the source\n- The Letta V1 Python API server is retired and unsupported, and the letta-ai/letta repository is now a landing page\n- The privacy policy names no legal entity or date and says hosted message data may train future models\n\n\n\n## Before you call it (notes for agents)\n\n1. Start headless runs with an explicit permission mode such as `standard` or `strict`; the default auto-approves tools\n2. Pass `--backend local` for work that must stay on the machine, since Letta Cloud is the default\n3. Set LETTA_CODE_TELEM=0 in unattended runs if usage events must not be sent\n4. Use `letta -p --output-format json` for scripted runs and parse the JSON, not the terminal output\n5. Don't plan on the retired V1 REST server or `.af` AgentFile import; both are gone\n\n## Connect\n\nInstall:\n\n```bash\nnpm install -g @letta-ai/letta-code\n```\n\nHeadless / CI:\n\n```json\n{\n \"local\": \"letta --backend local\",\n \"run\": \"letta -p --output-format json \\\"\\u003ctask\\u003e\\\"\",\n \"server\": \"letta server\"\n}\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| goose | BB | 71.3 | 165 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/goose.md |\n| AXLR | BB | 70.6 | 197 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/axlr.md |\n| OpenHands | BB | 70.3 | 206 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/openhands.md |\n| OpenCode | B | 68.8 | 269 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/opencode.md |\n| Qwen Code | B | 68.7 | 273 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/qwen-code.md |\n| Kilo Code CLI | B | 68 | 295 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/kilo-code-cli.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- The letta-ai/letta repository is now a landing page. Its README says the current source lives in letta-ai/letta-code and that the retired Letta V1 API server is kept on an archive branch, and its SECURITY.md says that server receives no fixes or security updates (source: \u003chttps://github.com/letta-ai/letta\u003e)\n- DEFAULT_PERMISSION_MODE is `unrestricted` in src/permissions/mode.ts, which migrates the older `bypassPermissions` and `fullAccess` values to it (source: \u003chttps://github.com/letta-ai/letta-code/blob/main/src/permissions/mode.ts\u003e)\n- src/index.ts initialises telemetry with the comment \"enabled by default, opt-out via LETTA_CODE_TELEM=0\" (source: \u003chttps://github.com/letta-ai/letta-code/blob/main/src/index.ts\u003e)\n- The README says Letta Cloud is the default backend, chosen at first launch, and AgentFile (.af) export and import have been removed (source: \u003chttps://github.com/letta-ai/letta-code/blob/main/README.md\u003e)\n- v0.34.42 tagged on 6 November 2026; 398 tags in the repository, which was created on 25 October 2025 (source: \u003chttps://github.com/letta-ai/letta-code\u003e)\n- Letta's seed round of $10 million, led by Felicis, was announced on 24 September 2024 (source: \u003chttps://prnewswire.com/news-releases/berkeley-ai-research-lab-spinout-letta-raises-10m-seed-financing-led-by-felicis-to-build-ai-with-memory-302257004.html\u003e)\n\n- #18 of 56 in Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1500 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n- #12 of 26 in Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md\n- All 353 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md\n\n## Compare\n\n- [Agent Zero vs Letta](https://www.anchorterminal.com/compare/agent-zero-vs-letta.md): D 46 vs C 59.7\n- [Aider vs Letta](https://www.anchorterminal.com/compare/aider-vs-letta.md): D 49.1 vs C 59.7\n- [Amp vs Letta](https://www.anchorterminal.com/compare/amp-vs-letta.md): C 55.5 vs C 59.7\n- [Antigravity CLI vs Letta](https://www.anchorterminal.com/compare/antigravity-cli-vs-letta.md): C 54.7 vs C 59.7\n- [Auggie CLI vs Letta](https://www.anchorterminal.com/compare/auggie-vs-letta.md): D 49.3 vs C 59.7\n- [AXLR vs Letta](https://www.anchorterminal.com/compare/axlr-vs-letta.md): BB 70.6 vs C 59.7\n- [Claude Code vs Letta](https://www.anchorterminal.com/compare/claude-code-vs-letta.md): D 53.6 vs C 59.7\n- [Cline vs Letta](https://www.anchorterminal.com/compare/cline-vs-letta.md): D 52.8 vs C 59.7\n- [Conductor vs Letta](https://www.anchorterminal.com/compare/conductor-vs-letta.md): E 41.3 vs C 59.7\n- [Crush vs Letta](https://www.anchorterminal.com/compare/crush-vs-letta.md): D 49.8 vs C 59.7\n- [Cursor CLI vs Letta](https://www.anchorterminal.com/compare/cursor-cli-vs-letta.md): F 35.4 vs C 59.7\n- [DeepSeek Harness (dsh) vs Letta](https://www.anchorterminal.com/compare/deepseek-harness-vs-letta.md): D 48.5 vs C 59.7\n- [dsh-superagent (DeepSeek) vs Letta](https://www.anchorterminal.com/compare/deepseek-superagent-vs-letta.md): E 42.1 vs C 59.7\n- [Devin vs Letta](https://www.anchorterminal.com/compare/devin-vs-letta.md): C 57.3 vs C 59.7\n- [Droid CLI vs Letta](https://www.anchorterminal.com/compare/droid-cli-vs-letta.md): C 57.2 vs C 59.7\n- [Pi vs Letta](https://www.anchorterminal.com/compare/earendil-pi-vs-letta.md): B 62.6 vs C 59.7\n- [Emdash vs Letta](https://www.anchorterminal.com/compare/emdash-vs-letta.md): D 53.9 vs C 59.7\n- [Gemini CLI vs Letta](https://www.anchorterminal.com/compare/gemini-cli-vs-letta.md): B 64.8 vs C 59.7\n- [GitHub Copilot CLI vs Letta](https://www.anchorterminal.com/compare/github-copilot-cli-vs-letta.md): C 56 vs C 59.7\n- [goose vs Letta](https://www.anchorterminal.com/compare/goose-vs-letta.md): BB 71.3 vs C 59.7\n- [Harness² vs Letta](https://www.anchorterminal.com/compare/harness2-vs-letta.md): E 42 vs C 59.7\n- [HarnessRouter vs Letta](https://www.anchorterminal.com/compare/harnessrouter-vs-letta.md): D 47.7 vs C 59.7\n- [Jules vs Letta](https://www.anchorterminal.com/compare/jules-vs-letta.md): E 45.1 vs C 59.7\n- [Junie CLI vs Letta](https://www.anchorterminal.com/compare/junie-vs-letta.md): D 49 vs C 59.7\n- [Kilo Code CLI vs Letta](https://www.anchorterminal.com/compare/kilo-code-cli-vs-letta.md): B 68 vs C 59.7\n- [Kimi Code CLI vs Letta](https://www.anchorterminal.com/compare/kimi-code-cli-vs-letta.md): C 58.1 vs C 59.7\n- [Kiro CLI vs Letta](https://www.anchorterminal.com/compare/kiro-cli-vs-letta.md): C 59.8 vs C 59.7\n- [Letta vs mini-swe-agent](https://www.anchorterminal.com/compare/letta-vs-mini-swe-agent.md): C 59.7 vs C 59\n- [Letta vs MiniMax Code](https://www.anchorterminal.com/compare/letta-vs-minimax-code.md): C 59.7 vs B 66.1\n- [Letta vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/letta-vs-mistral-vibe-cli.md): C 59.7 vs C 58.4\n- [Letta vs Muse Code](https://www.anchorterminal.com/compare/letta-vs-muse-code.md): C 59.7 vs C 56.2\n- [Letta vs OpenAI Agents API](https://www.anchorterminal.com/compare/letta-vs-openai-agents-api.md): C 59.7 vs BB 73.3\n- [Letta vs OpenAI Codex](https://www.anchorterminal.com/compare/letta-vs-openai-codex.md): C 59.7 vs BB 73.5\n- [Letta vs OpenCode](https://www.anchorterminal.com/compare/letta-vs-opencode.md): C 59.7 vs B 68.8\n- [Letta vs OpenHands](https://www.anchorterminal.com/compare/letta-vs-openhands.md): C 59.7 vs BB 70.3\n- [Letta vs OpenMausBot](https://www.anchorterminal.com/compare/letta-vs-openmausbot.md): C 59.7 vs B 65.4\n- [Letta vs Orca](https://www.anchorterminal.com/compare/letta-vs-orca.md): C 59.7 vs C 57.4\n- [Letta vs Paseo](https://www.anchorterminal.com/compare/letta-vs-paseo.md): C 59.7 vs B 62.1\n- [Letta vs Prime Agent](https://www.anchorterminal.com/compare/letta-vs-prime-agent.md): C 59.7 vs C 56.8\n- [Letta vs Qoder CLI](https://www.anchorterminal.com/compare/letta-vs-qoder-cli.md): C 59.7 vs C 59.5\n- [Letta vs Qwen Code](https://www.anchorterminal.com/compare/letta-vs-qwen-code.md): C 59.7 vs B 68.7\n- [Letta vs Mirror CLI](https://www.anchorterminal.com/compare/letta-vs-reflection-mirror.md): C 59.7 vs C 57.2\n- [Letta vs Rovo Dev CLI](https://www.anchorterminal.com/compare/letta-vs-rovo-dev-cli.md): C 59.7 vs E 44.1\n- [Letta vs Sculptor](https://www.anchorterminal.com/compare/letta-vs-sculptor.md): C 59.7 vs D 53.1\n- [Letta vs T3 Code](https://www.anchorterminal.com/compare/letta-vs-t3-code.md): C 59.7 vs D 51.9\n- [Letta vs Traycer](https://www.anchorterminal.com/compare/letta-vs-traycer.md): C 59.7 vs C 57\n- [Letta vs Unstoppable](https://www.anchorterminal.com/compare/letta-vs-unstoppable.md): C 59.7 vs F 34.7\n- [Letta vs Verdent](https://www.anchorterminal.com/compare/letta-vs-verdent.md): C 59.7 vs E 39.7\n- [Letta vs Vibe-Trading](https://www.anchorterminal.com/compare/letta-vs-vibe-trading.md): C 59.7 vs C 57.8\n- [Letta vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/letta-vs-warp.md): C 59.7 vs C 57.6\n- [Clawboo vs Letta](https://www.anchorterminal.com/compare/clawboo-vs-letta.md): C 61.4 vs C 59.7\n- [CLI Manager vs Letta](https://www.anchorterminal.com/compare/cli-manager-vs-letta.md): B 66.4 vs C 59.7\n- [Harness vs Letta](https://www.anchorterminal.com/compare/harness-autonomous-vs-letta.md): C 60.9 vs C 59.7\n- [Letta vs Paperclip](https://www.anchorterminal.com/compare/letta-vs-paperclip.md): C 59.7 vs D 52.6\n- [Letta vs Parallax](https://www.anchorterminal.com/compare/letta-vs-parallax-agents.md): C 59.7 vs E 38.1\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on letta.com or one of its subdomains, or the README at the root of github.com/letta-ai/letta-code. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"letta\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/letta\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/letta.svg\" alt=\"Letta on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![Letta on Anchor Terminal](https://www.anchorterminal.com/badges/letta.svg)](https://www.anchorterminal.com/tools/letta)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/letta\"\u003eLetta on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Letta is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/letta-dark.png\n- Light: https://www.anchorterminal.com/assets/share/letta-light.png\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Agent harnesses", "url": "https://www.anchorterminal.com/categories/agent-harnesses" }, { "name": "Letta", "url": "" } ], "description": "Letta, from the MemGPT team, is an open-source agent harness (formerly Letta Code) for stateful agents that keep memory blocks, skills and conversations across sessions, used from a CLI, chat.letta.com, messaging channels or the Agent SDK, with Letta Cloud.", "facts": [ "rank #684 of 1486", "OAuth or key auth", "0 desk reviews" ], "h1": "Letta", "image": "https://www.anchorterminal.com/assets/og/tools-letta.png", "path": "/tools/letta", "published": "2026-10-01", "section": "tools", "title": "Letta review (2026): pricing, alternatives and grade C", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/tools/letta" }, "tokens": { "markdown": 7450, "slim": 1280 }, "version": 1 }