zeroclaw的使用问题

问题描述：

有使用zeroclaw的大佬吗，发现改成三方的模型配置后就报错：

zeroclaw agent -m "你好，测试一下" 2026-02-25T12:49:13.551590Z INFO zeroclaw::config::schema: Config loaded path=/root/.zeroclaw/config.toml workspace=/root/.zeroclaw/workspace source="default" initialized=false 2026-02-25T12:49:13.553029Z INFO zeroclaw::agent::loop_: Memory initialized backend="sqlite" 2026-02-25T12:49:13.554624Z WARN zeroclaw::providers::reliable: Non-retryable error, moving on provider="custom:https://api.hotaruapi.top" model="claude-sonnet-4.6" error=Custom API key not set. Run `zeroclaw onboard` or set the appropriate env var. 2026-02-25T12:49:13.554652Z WARN zeroclaw::providers::reliable: Exhausted retries, trying next provider/model provider="custom:https://api.hotaruapi.top" model="claude-sonnet-4.6" Error: All providers/models failed. Attempts: provider=custom:https://api.hotaruapi.top model=claude-sonnet-4.6 attempt 1/3: non_retryable; error=Custom API key not set. Run `zeroclaw onboard` or set the appropriate env var.

配置是：

~/.zeroclaw/config.toml default_provider = "custom:https://anyrouter.top/" default_model = "claude-sonnet-4.6" default_temperature = 0.7 model_routes = [] embedding_routes = [] [model_providers] [observability] backend = "none" runtime_trace_mode = "none" runtime_trace_path = "state/runtime-trace.jsonl" runtime_trace_max_entries = 200 [autonomy] level = "supervised" workspace_only = true allowed_commands = [ "git", "npm", "cargo", "ls", "cat", "grep", "find", "echo", "pwd", "wc", "head", "tail", "date", ] forbidden_paths = [ "/etc", "/root", "/home", "/usr", "/bin", "/sbin", "/lib", "/opt", "/boot", "/dev", "/proc", "/sys", "/var", "/tmp", "~/.ssh", "~/.gnupg", "~/.aws", "~/.config", ] max_actions_per_hour = 20 max_cost_per_day_cents = 500 require_approval_for_medium_risk = true block_high_risk_commands = true shell_env_passthrough = [] auto_approve = [ "file_read", "memory_recall", ] always_ask = [] allowed_roots = [] non_cli_excluded_tools = [] [security.sandbox] backend = "auto" firejail_args = [] [security.resources] max_memory_mb = 512 max_cpu_time_seconds = 60 max_subprocesses = 10 memory_monitoring = true [security.audit] enabled = true log_path = "audit.log" max_size_mb = 100 sign_events = false [security.otp] enabled = false method = "totp" token_ttl_secs = 30 cache_valid_secs = 300 gated_actions = [ "shell", "file_write", "browser_open", "browser", "memory_forget", ] gated_domains = [] gated_domain_categories = [] [security.estop] enabled = false state_file = "~/.zeroclaw/estop-state.json" require_otp_to_resume = true [runtime] kind = "native" [runtime.docker] image = "alpine:3.20" network = "none" memory_limit_mb = 512 cpu_limit = 1.0 read_only_rootfs = true mount_workspace = true allowed_workspace_roots = [] [reliability] provider_retries = 2 provider_backoff_ms = 500 fallback_providers = [] api_keys = [] channel_initial_backoff_secs = 2 channel_max_backoff_secs = 60 scheduler_poll_secs = 15 scheduler_retries = 2 [reliability.model_fallbacks] [scheduler] enabled = true max_tasks = 64 max_concurrent = 4 [agent] compact_context = false max_tool_iterations = 10 max_history_messages = 50 parallel_tools = false tool_dispatcher = "auto" [skills] open_skills_enabled = false prompt_injection_mode = "full" [query_classification] enabled = false rules = [] [heartbeat] enabled = false interval_minutes = 30 [cron] enabled = true max_run_history = 50 [channels_config] cli = true message_timeout_secs = 300 [memory] backend = "sqlite" auto_save = true hygiene_enabled = true archive_after_days = 7 purge_after_days = 30 conversation_retention_days = 30 embedding_provider = "none" embedding_model = "text-embedding-3-small" embedding_dimensions = 1536 vector_weight = 0.7 keyword_weight = 0.3 min_relevance_score = 0.4 embedding_cache_size = 10000 chunk_max_tokens = 512 response_cache_enabled = false response_cache_ttl_minutes = 60 response_cache_max_entries = 5000 snapshot_enabled = false snapshot_on_hygiene = false auto_hydrate = true [memory.qdrant] collection = "zeroclaw_memories" [storage.provider.config] provider = "" schema = "public" table = "memories" [tunnel] provider = "none" [gateway] port = 42617 host = "127.0.0.1" require_pairing = true allow_public_bind = false paired_tokens = [] pair_rate_limit_per_minute = 10 webhook_rate_limit_per_minute = 60 trust_forwarded_headers = false rate_limit_max_keys = 10000 idempotency_ttl_secs = 300 idempotency_max_keys = 10000 [composio] enabled = false entity_id = "default" [secrets] encrypt = true [browser] enabled = false allowed_domains = [] backend = "agent_browser" native_headless = true native_webdriver_url = "http://127.0.0.1:9515" [browser.computer_use] endpoint = "http://127.0.0.1:8787/v1/actions" timeout_ms = 15000 allow_remote_endpoint = false window_allowlist = [] [http_request] enabled = false allowed_domains = [] max_response_size = 1000000 timeout_secs = 30 [multimodal] max_images = 4 max_image_size_mb = 5 allow_remote_fetch = false [web_fetch] enabled = false allowed_domains = ["*"] blocked_domains = [] max_response_size = 500000 timeout_secs = 30 [web_search] enabled = false provider = "duckduckgo" max_results = 5 timeout_secs = 15 [proxy] enabled = false no_proxy = [] scope = "zeroclaw" services = [] [identity] format = "openclaw" [cost] enabled = false daily_limit_usd = 10.0 monthly_limit_usd = 100.0 warn_at_percent = 80 allow_override = false [cost.prices."google/gemini-1.5-pro"] input = 1.25 output = 5.0 [cost.prices."openai/gpt-4o-mini"] input = 0.15 output = 0.6 [cost.prices."anthropic/claude-3.5-sonnet"] input = 3.0 output = 15.0 [cost.prices."openai/o1-preview"] input = 15.0 output = 60.0 [cost.prices."google/gemini-2.0-flash"] input = 0.1 output = 0.4 [cost.prices."openai/gpt-4o"] input = 5.0 output = 15.0 [cost.prices."anthropic/claude-opus-4-20250514"] input = 15.0 output = 75.0 [cost.prices."anthropic/claude-3-haiku"] input = 0.25 output = 1.25 [cost.prices."anthropic/claude-sonnet-4-20250514"] input = 3.0 output = 15.0 [peripherals] enabled = false boards = [] [agents] [hooks] enabled = true [hooks.builtin] command_logger = false [hardware] enabled = false transport = "None" baud_rate = 115200 workspace_datasheets = false [transcription] enabled = false api_url = "https://api.groq.com/openai/v1/audio/transcriptions" model = "whisper-large-v3-turbo" max_duration_secs = 120

配置zeroclaw使用GPT配置：

root@keke:~# cat .zeroclaw/config.toml default_provider = "custom:https://anyrouter.top/" default_model = "gpt-5.4" api_key = "xxxx" default_temperature = 0.7 model_routes = [] embedding_routes = []

配置claude使用配置：

default_provider = "anthropic-custom:https://anyrouter.top/" default_model = "claude-sonnet-4-20250514" api_key = "xxxx" default_temperature = 0.7 model_routes = [] embedding_routes = []

最近在看如何用zeroclaw去绑定微信claw的机器人，好像目前只支持openclaw，不过openclaw占用资源有点高！

网友解答：

---

--【壹】--：

蛤？ zeroClaw的核心开发者被T了？我刚卯准这个小龙虾准备下手呢

---

--【贰】--：

这个和openclaw的有点不一样，我最后解决这个问题用的是这个配置：

default_provider = "anthropic-custom:https://anyrouter.top/" default_model = "claude-sonnet-4-6" api_key = "sk-xxxx"

然后才可以了：

zeroclaw agent -m "你好，测试一下" 2026-02-25T13:55:43.091805Z INFO zeroclaw::config::schema: Config loaded path=/root/.zeroclaw/config.toml workspace=/root/.zeroclaw/workspace source="default" initialized=false 2026-02-25T13:55:43.093397Z INFO zeroclaw::agent::loop_: Memory initialized backend="sqlite" 你好！🦀 测试收到，一切正常！有什么需要帮忙的吗？

---

--【叁】--：

就是折腾，搞来搞去的，还不算成熟吧。

---

--【肆】--：

个人觉得这种json配置的维护起来简直是灾难

---

--【伍】--：

实测发现不支持MCP、技能运行不了脚本。
实际上这2个issue之前有pr，也被合并进了main分支，然而这个项目之前main、master分支混用，前几天刚把main删了，反而导致closed issue又被重新open了。此外release里版本号乱更新，从v0.1.8到v0.1.7再到v0.1.9。整体下来感觉管理比较混乱

---

--【陆】--：

尝试过zeroclaw、copaw以及openclaw，感觉zeroclaw完成度比较低，还是建议等等后续版本。copaw易用性比较好，喜欢折腾openclaw更合适

---

--【柒】--：

这个确实，而却容易安装。我尝试在旧手机安装copaw和openclaw都失败了，就zeroclaw的release版本直接可用

---

--【捌】--：

是这样的！

---

--【玖】--：

zeroclaw支持千问code plan的key吗？我这一直报仅限指定代理使用 在openclaw中可以正常使用

---

--【拾】--：

应该是支持你直接改模型就可以！

---

--【拾壹】--：

看重的是它的占用内存低特点！

---

--【拾贰】--：

这个项目的主要开发者好像被T了 所有可以抛弃了

---

--【拾叁】--：

安装给出的配置文件直接用就可以了，摸索出来其实也没啥！

---

--【拾肆】--：

唉，好不容易找到个，只好再去找别的了

---

--【拾伍】--：

如果想让你的claw机器人更加好用，请直接安装这几个skills：

Clawhub https://clawhub.ai npm i -g clawhub Tavily 如果你的openclaw是新的，没有联网，可以先把tavily搭起来。 clawhub install tavily-search Agent-Reach https://github.com/Panniantong/Agent-Reach?tab=readme-ov-file ClawFeed https://github.com/kevinho/clawfeed Multi Search Engine https://github.com/sanjay3290/ai-skills/tree/main/skills/deep-research x-reader https://github.com/runesleo/x-reader BrowserWing https://github.com/browserwing/browserwing/blob/main/README.zh-CN.md ModSearch https://github.com/liustack/modsearch/blob/main/README.zh-CN.md ClawFeed https://github.com/kevinho/clawfeed Free Ride https://clawhub.ai/Shaivpidadi/free-ride find-skills clawhub install find-skills

---

--【拾陆】--：

nanobot 之类的太多了

---

--【拾柒】--：

其实吧安装和配置还是有点复杂的 编译后资源占用确实好点

---

--【拾捌】--：

这项目完成度高么

---

--【拾玖】--：

provider最后需要加/v1,还需要配置api_key