返回资讯中心
外部精选
软件工程
#开发者实时流

Albedo 发布 pre-alpha 版本,为 AI agent 提供长期运行环境

来源标题:Albedo: Long running, efficient homes for your agents

Albedo 以 pre-alpha 形式发布,定位是为 AI agent 提供长期运行、高效的家。它支持 ChatGPT、Claude、Gemini、Kimi、GLM、DeepSeek 等多种模型,并展示了一个在本地代码库里统计 Gleam 模块行数的 agent 运行示例。

Hacker News 最新icy2026/11/16 · 昨天30 分钟阅读

以下正文由 AI 翻译自 Hacker News 最新(原文版权归原站所有),可能存在偏差,重要内容请以原文为准。

为你的 agent 提供长时间运行、高效的家(pre-alpha) chatgpt claude gemini kimi glm deepseek 以及更多 向下滚动,访问其中一个 ↓ survey · idle · done ❚❚跳到结尾↺重放 ✦ albedo 运行于 ~/Developer/albedoclaude-opus-5-5:medium 你 只读,不要编辑任何内容:src/albedo 下哪些 gleam 模块按行数算是最大的?按子系统展示前 10 个,并告诉我哪一个最值得拆分,以及为什么。 思考我想用一个快速的 Python 脚本统计 src/albedo 下 gleam 文件的行数。 ▸python · import os · 10 行 · 输出 26 行61msimport os from pathlib import Path root=Path("/Users/regent/Developer/albedo/src/albedo") rows=[] for p in root.rglob(".gleam"): n=sum(1 for _ in open(p,encoding="utf-8",errors="replace")) rows.append((n,str(p.relative_to(root)))) rows.sort(reverse=True) print(len(rows), sum(r[0] for r in rows)) for n,p in rows[:25]: print(n,p) 270 87917 3939 daemon/session.gleam 2655 daemon/conversation.gleam 1803 daemon/http_sessions.gleam 1573 harness/runtime.gleam 1382 daemon/registry.gleam 1338 harness/loop.gleam 1117 daemon/server.gleam 1038 harness/extension.gleam 1029 harness/extensions/snapcompact/extension.gleam 1023 harness/extensions/webhooks/ledger.gleam 947 harness/compaction.gleam 946 harness/extensions/lcm/extension.gleam 930 daemon/quota.gleam 928 harness/extensions/python/kernel.gleam 922 daemon/http_api.gleam 901 daemon/operations.gleam 872 harness/extensions/artifacts/ledger.gleam 846 harness/extensions/proxy/chat.gleam 831 daemon/requests.gleam 829 harness/extensions/discord/ledger.gleam 795 daemon/folders.gleam 792 daemon/http_transcript.gleam 775 daemon/http_resources.gleam 708 daemon/family.gleam 706 harness/extensions/discord/ingest.gleam ▸读取 src/albedo/ +63列出src/albedo/ 读取text_scalars.gleam 读取clock.gleam 读取openai_api.gleam 读取shared.gleam 读取actor_call.gleam 列出openai_api/ 读取openai_api/responses.gleam 读取openai_api/request.gleam 读取openai_api/decoding.gleam 读取openai_api/types.gleam 读取openai_api/sse.gleam 读取openai_api/transport.gleam 读取openai_api/fields.gleam 读取openai_api/reasoning.gleam 读取openai_api/chat.gleam 读取openai_api/replay.gleam 读取openai_api/stream.gleam 列出harness/ 读取harness/accounts.gleam 读取harness/extension.gleam 读取harness/capability_catalog.gleam 读取harness/capabilities.gleam 读取harness/instruction_files.gleam 读取harness/protect.gleam 读取harness/rpc.gleam 读取harness/rotation.gleam 读取harness/hook.gleam 读取harness/ssh.gleam 读取harness/settings.gleam 读取harness/search.gleam 读取harness/credentials.gleam 读取harness/host.gleam 读取harness/page.gleam 读取harness/languages.gleam 读取harness/compaction.gleam 读取harness/web_search.gleam 读取harness/usage_feed.gleam 读取harness/cache_fade.gleam 读取harness/context_limits.gleam 读取harness/location.gleam 读取harness/vcs.gleam 读取harness/links.gleam 读取harness/tool.gleam 读取harness/cache_ttl.gleam 读取harness/runtime.gleam 读取harness/project_files.gleam 读取harness/extensions.gleam 读取harness/command.gleam 读取harness/oauth.gleam 读取harness/client_api.gleam 读取harness/loop.gleam 列出daemon/ 读取daemon/events.gleam 读取daemon/http_active_output.gleam 读取daemon/http_coding.gleam 读取daemon/http_resources.gleam 读取daemon/note.gleam 读取daemon/operations.gleam 读取daemon/http_wire.gleam 读取daemon/stream_trace.gleam 读取daemon/store.gleam 读取daemon/session_preferences.gleam 读取daemon/http_stream.gleam 部分活动未被捕获;此列表不完整 思考270 个文件、88k 行,比预期小,但就这样吧。对于“按子系统前 10”,我还应该计算各子系统的总量,然后检查 session.gleam 的结构,判断它是否需要拆分,看看是否已有 session_.gleam 文件来自之前的部分拆分。 ▸python · from collections import defaultdict · 16 行 · 输出 17 行8msfrom collections import defaultdict def sub(p): parts=p.split("/") if parts[0]=="harness" and len(parts)>2 and parts[1]=="extensions": return "harness/extensions/"+parts[2] return "/".join(parts[:-1]) or "." tot=defaultdict(lambda:[0,0]) for n,p in rows: t=tot[sub(p)]; t[0]+=n; t[1]+=1 for k,v in sorted(tot.items(),key=lambda x:-x[1][0])[:12]: print(v,k) import re for f in ["daemon/session.gleam","daemon/conversation.gleam"]: src=(root/f).read_text() fns=re.findall(r'^(pub )?fn (\w+)',src,re.M) types=re.findall(r'^(pub )?(?:opaque )?type (\w+)',src,re.M) print(f,len(fns),"fns",sum(1 for a,_ in fns if a),"pub; types",[t for _,t in types]) imports=re.findall(r'^import ([\w/]+)',src,re.M); print(len(imports),"imports") print(sorted(p for _,p in rows if p.startswith("daemon/session"))) [34801, 79] daemon [10748, 33] harness [3360, 8] harness/extensions/discord [3101, 10] harness/extensions/python [2915, 11] openai_api [2653, 8] harness/runtime [2583, 7] harness/extensions/antigravity [2052, 5] harness/extensions/webhooks [1958, 6] harness/extensions/claude [1892, 4] harness/extensions/lcm [1812, 5] harness/extensions/artifacts [1357, 11] harness/extensions/paperclips daemon/session.gleam 141 个函数,其中 37 个 pub;类型 ['Session', 'Cursor', 'Page', 'Capture', 'Summary', 'StatusRead', 'InputCancellation', 'Interruption', 'Report', 'ModelSelection', 'SubmissionError', 'Message', 'State', 'ClosureEvent', 'Unobserved'] 52 个 import daemon/conversation.gleam 96 个函数,其中 62 个 pub;类型 ['Info', 'RunCompletion', 'Preview', 'CapturedInfo', 'Creation', 'CreationRecord', 'ChildCreation', 'Stage', 'Snapshot', 'SourceStats', 'FoldStep', 'FitSchedule', 'LoadedRow', 'Direction', 'Range', 'TranscriptOwnership', 'Continuation', 'SourcePage', 'ToolAssociation', 'PinnedPrompt'] 31 个 import

(原文较长,此处译出前 6000 字,完整内容请点「打开原文」。)

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →