[{"data":1,"prerenderedAt":594},["ShallowReactive",2],{"tool-cline-en":3},{"slug":4,"published":5,"minutes":6,"category":7,"tags":8,"keywords":14,"about":23,"sources":30,"cover":60,"og":61,"expertise":62,"locales":63,"lang":64,"title":67,"description":68,"coverAlt":69,"url":70,"pricing":71,"kind":9,"metaTitle":72,"takeaways":73,"faq":79,"toc":92,"blocks":117,"others":365},"cline","2026-06-16",11,"agents",[9,10,11,12,13],"Coding agent","Plan and Act","Checkpoints","MCP","Open source",[15,16,17,18,19,20,21,22],"cline coding agent","cline vs claude code","cline vs cursor","cline cli headless","coding agent auto approve","cline checkpoints","cline pass pricing","open source coding agent",[24,27],{"name":25,"url":26},"Cline","https:\u002F\u002Fgithub.com\u002Fcline\u002Fcline",{"name":28,"url":29},"Model Context Protocol","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FModel_Context_Protocol",[31,34,37,40,43,46,49,52,55,58],{"title":32,"url":33},"Cline docs: Overview","https:\u002F\u002Fdocs.cline.bot\u002Fintroduction\u002Foverview",{"title":35,"url":36},"Cline docs: Plan and Act mode","https:\u002F\u002Fdocs.cline.bot\u002Fcore-workflows\u002Fplan-and-act",{"title":38,"url":39},"Cline docs: CLI reference","https:\u002F\u002Fdocs.cline.bot\u002Fcli\u002Fcli-reference",{"title":41,"url":42},"Cline docs: Auto Approve and YOLO mode","https:\u002F\u002Fdocs.cline.bot\u002Ffeatures\u002Fauto-approve",{"title":44,"url":45},"Cline docs: Checkpoints","https:\u002F\u002Fdocs.cline.bot\u002Ffeatures\u002Fcheckpoints",{"title":47,"url":48},"Cline docs: MCP","https:\u002F\u002Fdocs.cline.bot\u002Fmcp\u002Fmcp-overview",{"title":50,"url":51},"Cline docs: Rules","https:\u002F\u002Fdocs.cline.bot\u002Fcustomization\u002Fcline-rules",{"title":53,"url":54},"Cline docs: ClinePass","https:\u002F\u002Fdocs.cline.bot\u002Fgetting-started\u002Fclinepass",{"title":56,"url":57},"Cline pricing","https:\u002F\u002Fcline.bot\u002Fpricing",{"title":59,"url":26},"cline\u002Fcline on GitHub","\u002Fimages\u002Fblog\u002Fcline\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fcline\u002Fog.jpg","ai-engineer",[64,65,66],"en","de","hu","Cline, reviewed: an open coding agent that gives you every model and none of the guardrails","Cline is an Apache-2.0 coding agent for VS Code, JetBrains and the terminal. What Plan and Act, checkpoints and auto-approve actually guarantee, and where the safety model leaks.","A prompt enters Plan mode, the agent explores without touching files, then Act mode applies the plan as a diff with a checkpoint after each step.","https:\u002F\u002Fcline.bot","Free · BYO API key","Cline, reviewed: an open coding agent · Balázs Csorba",[74,75,76,77,78],"Cline is Apache-2.0 and runs as a VS Code or JetBrains extension, a CLI, a desktop app and an SDK, all on the same agent core, so the approval model you learn in one place is the same in the others.","Plan mode cannot edit files or run commands by construction, which makes the plan a real artefact rather than a request the model is asked to honour.","Checkpoints commit to a separate shadow Git repository after every tool call, so rollback is cheap, at the cost of storing a full snapshot of the workspace per step on large repositories.","Auto-approve has no command allowlist: the model decides per call whether a command needs approval, and the CLI defaults to auto-approve true.","Because bring-your-own-key is the default, the security boundary is the provider, not the tool, and Cline adds no redaction, retention or audit layer of its own.",[80,83,86,89],{"q":81,"a":82},"Is Cline free?","The extension, CLI, desktop app and SDK are Apache-2.0 and free to install, with no seat fee. The model calls are not free unless you run a local model: Cline supports Claude, GPT, Gemini, Bedrock, Vertex, OpenRouter, Groq, Ollama and LM Studio, plus its own pay-as-you-go credits and ClinePass at $9.99 a month.",{"q":84,"a":85},"Is Cline safe to run with auto-approve on?","It is recoverable, not safe. Checkpoints snapshot the workspace after every tool call so you can roll the files back, but the agent still runs real commands on your machine while the snapshot is being written, and YOLO mode disables every check including file access outside the workspace. Run it on a branch, on a disposable machine, or inside a container.",{"q":87,"a":88},"Can Cline restrict which shell commands it runs?","Not with a built-in allow or deny list. The documentation states this plainly and points to a PreToolUse hook that cancels run_commands calls matching a pattern, which is the same mechanism used to enforce .clineignore now that .clineignore itself is being deprecated as a context filter.",{"q":90,"a":91},"Cline or Claude Code for an existing team?","Pick Cline when model choice is a policy requirement, when the bill must go to existing provider contracts, or when the team needs the SDK and CLI for automation. Pick Claude Code when you want one vendor's harness, one model's behaviour and one support path, and can accept the matching subscription.",[93,96,99,102,105,108,111,114],{"id":94,"title":95},"what-it-is","What Cline is",{"id":97,"title":98},"plan-and-act","Plan and Act, and why the split matters",{"id":100,"title":101},"getting-started","Getting started",{"id":103,"title":104},"pricing","What it costs",{"id":106,"title":107},"safety-model","The permission model, honestly",{"id":109,"title":110},"where-it-shingles","Where it shingle",{"id":112,"title":113},"verdict","Verdict",{"id":115,"title":116},"sources","Sources",[118,122,125,128,144,145,148,157,160,163,164,172,174,189,208,209,212,222,225,226,229,239,245,246,249,304,307,310,311,314,327,331,332],{"type":119,"content":120},"paragraph",[121],"Cline is a coding agent that runs where engineers already work, and it does not try to own the model. It ships as a VS Code and JetBrains extension, a CLI, a desktop app and an SDK, all built on one agent core published under Apache-2.0, and every one of them will connect to whatever provider the team has already bought. The position here is that this is the right default for anyone who has to justify the bill, and the wrong default for anyone who wants a guardrail they can rely on, because the permission model is softer than it looks.",{"type":119,"content":123},[124],"It competes directly with Claude Code, Cursor and the hosted coding assistants. Unlike those, it is not a product with a model attached but a harness with a model slot: the documentation lists Claude, GPT, Gemini, OpenRouter, AWS Bedrock, GCP Vertex, Groq, Cerebras, DeepSeek, local runtimes through Ollama and LM Studio, and anything speaking the OpenAI-compatible shape. That breadth is the feature, and it is also why comparing it to a closed product on quality is close to meaningless: most of what people praise or criticise about a coding agent is the model underneath.",{"type":126,"level":127,"id":94,"text":95},"heading",2,{"type":129,"ordered":130,"items":131},"list",false,[132,134,136,138,140,142],[133],"Apache-2.0, roughly 70,000 GitHub stars, 7,600 forks and 250-plus contributors, published as the cline CLI package and the @cline\u002Fsdk library.",[135],"The same agent core behind four surfaces: IDE extension, terminal CLI, desktop app for macOS, Windows and Linux, and a TypeScript SDK for embedding it elsewhere.",[137],"Plan mode and Act mode as separate states, with the option to run a different model in each.",[139],"Checkpoints on by default, committing a full snapshot of the workspace to a separate shadow Git repository after every tool call.",[141],"Per-category auto-approve toggles for reads, edits, commands, browser and MCP tools, plus a YOLO mode that turns all of them off.",[143],"MCP support with local STDIO servers and hosted Streamable HTTP endpoints, and rule files read from .clinerules, .cline\u002Frules, .cursorrules, .windsurfrules or AGENTS.md.",{"type":126,"level":127,"id":97,"text":98},{"type":119,"content":146},[147],"Plan mode is not a prompt. In that state the agent can read files, search and discuss, but it cannot modify a file or execute a command, and the conversation history carries over unchanged when Act mode starts. That makes the plan something the tool enforces rather than something the model is asked to remember, which is a materially better design than instructing a model to propose first.",{"type":149,"attrs":150,"inner":154,"caption":155},"diagram",{"viewBox":151,"role":152,"aria-labelledby":153},"0 0 720 320","img","d-cline-t d-cline-d","\u003Ctitle id=\"d-cline-t\">The Cline Plan and Act loop with checkpoints\u003C\u002Ftitle>\u003Cdesc id=\"d-cline-d\">A task enters Plan mode, where the agent reads files and searches but cannot write or run commands. Switching to Act mode carries the same conversation forward. Act mode then edits files and runs commands, and after every tool call a checkpoint is committed to a shadow Git repository. A restore returns the files, the task or both.\u003C\u002Fdesc>\u003Cdefs>\u003Cmarker id=\"cline-arrow\" viewBox=\"0 0 10 10\" refX=\"9\" refY=\"5\" markerWidth=\"7\" markerHeight=\"7\" orient=\"auto-start-reverse\">\u003Cpath d=\"M0 0L10 5L0 10z\" class=\"d-head\" \u002F>\u003C\u002Fmarker>\u003C\u002Fdefs>\u003Crect x=\"15\" y=\"130\" width=\"140\" height=\"64\" rx=\"10\" class=\"d-box\" \u002F>\u003Ctext x=\"85\" y=\"158\" text-anchor=\"middle\" class=\"d-text\">task\u003C\u002Ftext>\u003Ctext x=\"85\" y=\"180\" text-anchor=\"middle\" class=\"d-small\">what to build\u003C\u002Ftext>\u003Crect x=\"195\" y=\"30\" width=\"150\" height=\"64\" rx=\"10\" class=\"d-sky\" \u002F>\u003Ctext x=\"270\" y=\"58\" text-anchor=\"middle\" class=\"d-text\">plan mode\u003C\u002Ftext>\u003Ctext x=\"270\" y=\"80\" text-anchor=\"middle\" class=\"d-small\">read and search\u003C\u002Ftext>\u003Crect x=\"195\" y=\"230\" width=\"150\" height=\"64\" rx=\"10\" class=\"d-accent\" \u002F>\u003Ctext x=\"270\" y=\"258\" text-anchor=\"middle\" class=\"d-text\">act mode\u003C\u002Ftext>\u003Ctext x=\"270\" y=\"280\" text-anchor=\"middle\" class=\"d-small\">edit and run\u003C\u002Ftext>\u003Crect x=\"385\" y=\"130\" width=\"150\" height=\"64\" rx=\"10\" class=\"d-gold\" \u002F>\u003Ctext x=\"460\" y=\"158\" text-anchor=\"middle\" class=\"d-text\">checkpoint\u003C\u002Ftext>\u003Ctext x=\"460\" y=\"180\" text-anchor=\"middle\" class=\"d-small\">shadow git commit\u003C\u002Ftext>\u003Crect x=\"575\" y=\"30\" width=\"140\" height=\"64\" rx=\"10\" class=\"d-mint\" \u002F>\u003Ctext x=\"645\" y=\"58\" text-anchor=\"middle\" class=\"d-text\">diff\u003C\u002Ftext>\u003Ctext x=\"645\" y=\"80\" text-anchor=\"middle\" class=\"d-small\">review, revert\u003C\u002Ftext>\u003Crect x=\"575\" y=\"230\" width=\"140\" height=\"64\" rx=\"10\" class=\"d-box\" \u002F>\u003Ctext x=\"645\" y=\"258\" text-anchor=\"middle\" class=\"d-text\">restore\u003C\u002Ftext>\u003Ctext x=\"645\" y=\"280\" text-anchor=\"middle\" class=\"d-small\">files or task\u003C\u002Ftext>\u003Cpath d=\"M155 162H193\" class=\"d-line\" marker-end=\"url(#cline-arrow)\" \u002F>\u003Cpath d=\"M270 130V96\" class=\"d-line\" marker-end=\"url(#cline-arrow)\" \u002F>\u003Cpath d=\"M270 230V266\" class=\"d-line\" marker-end=\"url(#cline-arrow)\" \u002F>\u003Ctext x=\"282\" y=\"140\" class=\"d-label\">plan first\u003C\u002Ftext>\u003Cpath d=\"M345 62H573\" class=\"d-line\" marker-end=\"url(#cline-arrow)\" \u002F>\u003Cpath d=\"M345 262H573\" class=\"d-line\" marker-end=\"url(#cline-arrow)\" \u002F>\u003Cpath d=\"M460 194V162\" class=\"d-line\" marker-end=\"url(#cline-arrow)\" \u002F>\u003Ctext x=\"472\" y=\"212\" class=\"d-label\">after each tool\u003C\u002Ftext>\u003Cpath d=\"M535 162H270\" class=\"d-line d-dash\" marker-end=\"url(#cline-arrow)\" \u002F>\u003Ctext x=\"330\" y=\"150\" class=\"d-label\">more steps\u003C\u002Ftext>\u003Cpath d=\"M575 292V294\" class=\"d-line\" marker-end=\"url(#cline-arrow)\" \u002F>",[156],"Plan mode cannot write, so the plan is a constraint rather than a request. Act mode applies it, and every tool call is followed by a checkpoint in a separate Git repository that the project's own history never sees.",{"type":119,"content":158},[159],"Checkpoints are the other half of the design and deserve more attention than they get. After each file edit or command, Cline commits the current state of the working files to a shadow Git repository that is entirely separate from the project's real history. Three restore modes follow from that: restore the files and keep the conversation, restore the task and keep the code, or reset both. It is the reason auto-approve is defensible at all, and the documentation is candid that on very large repositories the snapshots cost storage and slow the agent down.",{"type":119,"content":161},[162],"Plan and Act can also point at different models, which is the cheapest cost lever in the whole product: a strong reasoning model for exploration and a cheap fast one for applying the plan. For small tasks the documentation recommends skipping planning entirely, because the planning pass is pure overhead when the answer is obvious.",{"type":126,"level":127,"id":100,"text":101},{"type":119,"content":165},[166,167,171],"The CLI is the surface worth learning first, because it is the only one where the approval defaults are visible and where the agent can run unattended. Headless mode switches on by itself when you pass ",{"tag":168,"children":169},"code",[170],"--json",", pipe stdin, or redirect stdout, which is a nice property for CI.",{"type":168,"code":173},"# Read every failing test and fix what caused them, then stop.\nset -euo pipefail\n\nnpm test 2>&1 | tee \u002Ftmp\u002Ffailures.log || true\n\n# Plan-only pass: no writes, no commands, just an analysis to review.\ncline -p \"Explain why these tests fail and what the smallest fix is\" \\\n  --json \u003C \u002Ftmp\u002Ffailures.log > \u002Ftmp\u002Fplan.jsonl\n\n# Apply pass on a clean branch, with a hard stop so a loop cannot burn the budget.\ncline \"Apply the fix for the failures listed in \u002Ftmp\u002Ffailures.log\" \\\n  --auto-approve true \\\n  --timeout 600 \\\n  --retries 3 \\\n  --model anthropic\u002Fclaude-sonnet-4-6 \\\n  | tee \u002Ftmp\u002Frun.log\n\n# Fail the job when the suite is still red, so the pipeline does not ship a broken tree.\nnpm test",{"type":119,"content":175},[176,177,180,181,184,185,188],"Three defaults in that invocation deserve scrutiny. ",{"tag":168,"children":178},[179],"--auto-approve"," defaults to true in the CLI, so unattended runs are the out-of-the-box behaviour, not the exception. ",{"tag":168,"children":182},[183],"--retries"," caps consecutive mistakes, which is the only guard against an agent looping on the same failing edit. And ",{"tag":168,"children":186},[187],"--timeout"," is the wall-clock stop that keeps a scheduled job from running until the budget is gone.",{"type":190,"variant":191,"title":192,"body":193},"callout","warn","The CLI has no command allowlist at all",[194],[195,196,199,200,203,204,207],"The documentation says so directly: to block shell commands you have to install a ",{"tag":168,"children":197},[198],"PreToolUse"," hook that cancels ",{"tag":168,"children":201},[202],"run_commands"," calls matching a pattern. The same mechanism is now the recommended way to enforce ",{"tag":168,"children":205},[206],".clineignore",", which is being deprecated precisely because it was never an access boundary: ignored files could still be read through an explicit mention or a shell command.",{"type":126,"level":127,"id":103,"text":104},{"type":119,"content":210},[211],"The software is free and the inference is not. The extension, CLI, desktop app and SDK carry no seat fee, so the marginal cost of running Cline is whatever the chosen provider charges for the tokens an agentic loop burns, and an agent loop burns many times more tokens than a chat because every tool result comes back into the context. There is no seat price to negotiate and no invoice from Cline for the open-source path.",{"type":129,"ordered":130,"items":213},[214,216,218,220],[215],"Bring your own key: pay the provider directly, under a contract and a spend limit the organisation already controls.",[217],"Cline usage-billing: one account, prepaid credits, one balance across the models Cline fronts, with some models tagged free for limited periods.",[219],"ClinePass at $9.99 a month, a flat subscription that the documentation advertises as two to five times the usage on a curated set of open coding models against standard API rates.",[221],"Enterprise: SSO, role-based access, centralised billing, audit logs, VPC deployment and OpenTelemetry, none of which exists in the free tier.",{"type":119,"content":223},[224],"The practical consequence is that cost control moves out of the tool and into the provider console. A team that wants a hard ceiling on agent spend needs either a provider that enforces one or a wrapper around the CLI that fails the run on a token or dollar budget, because Cline exposes usage in its session history and its enterprise dashboard but does not itself stop a run when a threshold is reached.",{"type":126,"level":127,"id":106,"text":107},{"type":119,"content":227},[228],"This is the part worth being blunt about. Auto-approve is evaluated per tool call against a category toggle, but there is no fixed allowlist of commands. The model marks each command as safe or requiring approval based on the command and its arguments, and the documentation gives examples rather than guarantees: build and test commands are usually safe, while installs, deletions, moves and in-place edits usually need approval. A security control that is implemented by asking a language model to classify a shell string is a speed bump, not a boundary.",{"type":129,"ordered":130,"items":230},[231,233,235,237],[232],"YOLO mode auto-approves everything: file operations anywhere on the machine, all terminal commands, browser actions, MCP tools and even the Plan to Act transition.",[234],"The read and edit toggles have an all-files variant, which extends access outside the workspace when the base toggle is on.",[236],"Scheduling, agent teams and subagents exist in the SDK, CLI and Kanban but not in the IDE extensions, so a control tested in one surface may not exist in another.",[238],"Subagents are read-only by construction, which is the one part of the tool where a capability limit is real rather than advisory.",{"type":190,"variant":240,"title":241,"body":242},"note","Run it where a mistake is cheap",[243],[244],"The combination that works is a throwaway branch or worktree, a container or a throwaway virtual machine, and a spend cap at the provider. Checkpoints then make the loop fast without making it safe, and the residual risk is whatever the agent ran before the snapshot caught up.",{"type":126,"level":127,"id":109,"text":110},{"type":119,"content":247},[248],"The fragmentation is the tax. Features land in the SDK and CLI first and reach the extensions later, which the documentation states outright for scheduling, agent teams and subagents. The JetBrains plugin is the sharpest version of the problem: the repository states plainly that JetBrains plugins are not being open-sourced, so the IDE that a large part of the European developer base runs on is the one surface a reviewer cannot audit.",{"type":250,"head":251,"rows":259},"table",[252,254,255,257],[253],"Dimension",[25],[256],"Claude Code",[258],"Cursor",[260,268,277,286,295],[261,263,265,267],[262],"Licence",[264],"Apache-2.0, source available",[266],"Proprietary",[266],[269,271,273,275],[270],"Model choice",[272],"Any provider, own key, local weights",[274],"Claude only",[276],"Several providers, own key",[278,280,282,284],[279],"Headless and CI",[281],"First-class CLI, SDK and cron scheduling",[283],"CLI, first-class",[285],"Cloud agents and CLI",[287,289,291,293],[288],"Command restriction",[290],"Hook-based, no built-in allowlist",[292],"Permission rules",[294],"Admin-controlled allow and deny",[296,298,300,302],[297],"Cost shape",[299],"Free software, provider bill",[301],"Subscription plus API",[303],"Subscription plus usage",{"type":119,"content":305},[306],"Context handling is the other soft spot, and it is not specific to Cline. An agent that reads files, runs tests, reads the failures and reads the diff again will spend most of its budget re-reading. The documented answer is subagents, which explore in parallel with their own context windows and return a short report, and memory bank files for structure. Both help, and neither changes the fact that an agentic session on a large repository is expensive in tokens relative to the value of the change.",{"type":119,"content":308},[309],"Finally, the tool's own security surface deserves the same scrutiny as any other agent: the repository has a security policy, and a project that lets an agent read files and run commands on a developer machine is a dependency with a shell. Treat the version as a pinned dependency, review the changelog before upgrades, and keep the provider keys scoped.",{"type":126,"level":127,"id":112,"text":113},{"type":119,"content":312},[313],"Cline is the best answer available for a team that has to choose its model, keep its data inside an existing provider contract, or automate agent work in CI without a vendor's permission system in the way. It is not a better version of a closed coding agent, and reviews that rank the two are comparing a harness to a model.",{"type":129,"ordered":315,"items":316},true,[317,319,321,323,325],[318],"Teams whose provider choice is a procurement decision rather than a preference.",[320],"Engineers automating repository work in CI, where the headless CLI and the SDK are the reason to adopt it.",[322],"Anyone building on top of an agent runtime, because @cline\u002Fsdk is the agent core rather than a wrapper.",[324],"Do not adopt it on the assumption that checkpoints make autonomy safe. They make it recoverable.",[326],"Do not adopt it where the command surface must be provably bounded without writing hooks, or where an unauditable IDE plugin disqualifies the tool.",{"type":190,"variant":240,"body":328},[329],[330],"The trade is explicit and worth stating plainly: you gain model choice, an auditable licence and real headless automation, and you pay for it with a permission model that leans on the model to classify commands and with features that arrive in the CLI before they arrive in the editor.",{"type":126,"level":127,"id":115,"text":116},{"type":129,"ordered":315,"items":333},[334,338,341,344,347,350,353,356,359,362],[335],{"tag":336,"href":33,"children":337},"a",[32],[339],{"tag":336,"href":36,"children":340},[35],[342],{"tag":336,"href":39,"children":343},[38],[345],{"tag":336,"href":42,"children":346},[41],[348],{"tag":336,"href":45,"children":349},[44],[351],{"tag":336,"href":48,"children":352},[47],[354],{"tag":336,"href":51,"children":355},[50],[357],{"tag":336,"href":54,"children":358},[53],[360],{"tag":336,"href":57,"children":361},[56],[363],{"tag":336,"href":26,"children":364},[59],[366,428,474,540],{"slug":367,"published":368,"minutes":369,"category":7,"tags":370,"keywords":374,"about":381,"sources":383,"cover":420,"og":421,"expertise":62,"locales":422,"lang":64,"title":423,"description":424,"coverAlt":425,"url":386,"pricing":426,"kind":427},"mcp-reference-servers","2026-09-25",9,[12,371,372,373],"Reference servers","Tool protocol","Server SDKs",[375,376,377,378,379,380],"mcp reference servers","modelcontextprotocol servers github","write an mcp server","mcp server examples","mcp server sdk","mcp server security",[382],{"name":28,"url":29},[384,387,390,393,396,399,402,405,408,411,414,417],{"title":385,"url":386},"MCP reference servers repository","https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers",{"title":388,"url":389},"Repository README and server list","https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers\u002Fblob\u002Fmain\u002FREADME.md",{"title":391,"url":392},"Security policy","https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers\u002Fblob\u002Fmain\u002FSECURITY.md",{"title":394,"url":395},"Release process and trusted publishing","https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers\u002Fblob\u002Fmain\u002FRELEASING.md",{"title":397,"url":398},"Filesystem server README","https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers\u002Fblob\u002Fmain\u002Fsrc\u002Ffilesystem\u002FREADME.md",{"title":400,"url":401},"Everything server feature list","https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers\u002Fblob\u002Fmain\u002Fsrc\u002Feverything\u002Fdocs\u002Ffeatures.md",{"title":403,"url":404},"MCP Registry","https:\u002F\u002Fregistry.modelcontextprotocol.io\u002F",{"title":406,"url":407},"Archived reference servers","https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers-archived",{"title":409,"url":410},"Model Context Protocol documentation","https:\u002F\u002Fmodelcontextprotocol.io\u002F",{"title":412,"url":413},"TypeScript MCP SDK","https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Ftypescript-sdk",{"title":415,"url":416},"Python MCP SDK","https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fpython-sdk",{"title":418,"url":419},"FastMCP on PyPI","https:\u002F\u002Fpypi.org\u002Fproject\u002Ffastmcp\u002F","\u002Fimages\u002Fblog\u002Fmcp-reference-servers\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fmcp-reference-servers\u002Fog.jpg",[64,65,66],"MCP reference servers: what they demonstrate and what they omit","A review of modelcontextprotocol\u002Fservers: seven reference servers, what each one teaches, the SDK versions behind them and why none of them should reach production.","Seven reference servers fanning out from a single MCP client over stdio","MIT","Protocol tooling",{"slug":429,"published":430,"minutes":431,"category":7,"tags":432,"keywords":436,"about":443,"sources":450,"cover":467,"og":468,"expertise":62,"locales":469,"lang":64,"title":470,"description":471,"coverAlt":472,"url":473,"pricing":71,"kind":9},"aider","2026-09-23",10,[9,433,434,435,13],"Terminal","Git workflow","BYO key",[429,437,438,439,440,22,441,442],"aider vs claude code","aider polyglot benchmark","ai pair programming terminal","aider leaderboard","aider architect mode","aider install",[444,447],{"name":445,"url":446},"Aider","https:\u002F\u002Faider.chat\u002F",{"name":448,"url":449},"Aider on GitHub","https:\u002F\u002Fgithub.com\u002FAider-AI\u002Faider",[451,453,456,459,462,464],{"title":452,"url":446},"Aider website",{"title":454,"url":455},"Aider LLM leaderboards","https:\u002F\u002Faider.chat\u002Fdocs\u002Fleaderboards\u002F",{"title":457,"url":458},"Aider linting and testing","https:\u002F\u002Faider.chat\u002Fdocs\u002Fusage\u002Flint-test.html",{"title":460,"url":461},"Aider token limits","https:\u002F\u002Faider.chat\u002Fdocs\u002Ftroubleshooting\u002Ftoken-limits.html",{"title":463,"url":449},"Aider repository on GitHub",{"title":465,"url":466},"aider-chat on PyPI","https:\u002F\u002Fpypi.org\u002Fproject\u002Faider-chat\u002F","\u002Fimages\u002Fblog\u002Faider\u002Fcover.webp","\u002Fimages\u002Fblog\u002Faider\u002Fog.jpg",[64,65,66],"Aider review: git-first pair programming in the terminal","A review of Aider 0.86.2, an Apache-2.0 terminal pair programmer whose benchmark ranks models honestly and whose release cadence has stopped.","Cover art for the Aider review: a terminal session turning a single request into a row of git commits","https:\u002F\u002Faider.chat",{"slug":475,"published":476,"minutes":431,"category":7,"tags":477,"keywords":482,"about":491,"sources":501,"cover":532,"og":533,"expertise":62,"locales":534,"lang":64,"title":535,"description":536,"coverAlt":537,"url":504,"pricing":538,"kind":539},"openai-agents-sdk","2026-09-11",[478,479,480,12,481],"Agent runtime","Tracing","Guardrails","Python",[483,484,485,486,487,488,489,490],"openai agents sdk","openai agents sdk vs langgraph","python agent framework comparison","openai agents sdk guardrails","agent run tracing tool calls","openai agents sdk human in the loop","openai-agents pypi","agents sdk vs responses api",[492,495,498],{"name":493,"url":494},"Model context protocol","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FModel_context_protocol",{"name":496,"url":497},"Software framework","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FSoftware_framework",{"name":499,"url":500},"Agentic AI","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAgentic_AI",[502,505,508,511,514,517,520,523,526,529],{"title":503,"url":504},"OpenAI Agents SDK documentation: Intro, and Agents SDK or Responses API","https:\u002F\u002Fopenai.github.io\u002Fopenai-agents-python\u002F",{"title":506,"url":507},"OpenAI Agents SDK documentation: Running agents","https:\u002F\u002Fopenai.github.io\u002Fopenai-agents-python\u002Frunning_agents\u002F",{"title":509,"url":510},"OpenAI Agents SDK documentation: Guardrails","https:\u002F\u002Fopenai.github.io\u002Fopenai-agents-python\u002Fguardrails\u002F",{"title":512,"url":513},"OpenAI Agents SDK documentation: Human-in-the-loop","https:\u002F\u002Fopenai.github.io\u002Fopenai-agents-python\u002Fhuman_in_the_loop\u002F",{"title":515,"url":516},"OpenAI Agents SDK documentation: Tracing","https:\u002F\u002Fopenai.github.io\u002Fopenai-agents-python\u002Ftracing\u002F",{"title":518,"url":519},"OpenAI Agents SDK documentation: Configuration","https:\u002F\u002Fopenai.github.io\u002Fopenai-agents-python\u002Fconfig\u002F",{"title":521,"url":522},"openai-agents 0.23.1 on PyPI, release history and licence","https:\u002F\u002Fpypi.org\u002Fproject\u002Fopenai-agents\u002F",{"title":524,"url":525},"OpenAI: The next evolution of the Agents SDK (15 April 2026)","https:\u002F\u002Fopenai.com\u002Findex\u002Fthe-next-evolution-of-the-agents-sdk\u002F",{"title":527,"url":528},"OpenAI API documentation: Agents, comparison of the three runtimes","https:\u002F\u002Fdevelopers.openai.com\u002Fapi\u002Fdocs\u002Fguides\u002Fagents",{"title":530,"url":531},"Arize: AI agent frameworks compared (1 October 2026)","https:\u002F\u002Farize.com\u002Fai-agents\u002Fagent-frameworks\u002F","\u002Fimages\u002Fblog\u002Fopenai-agents-sdk\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fopenai-agents-sdk\u002Fog.jpg",[64,65,66],"OpenAI Agents SDK: a small agent runtime with sharp edges","A review of the OpenAI Agents SDK: the runner loop, tracing, guardrails and approvals, plus what the release churn and the Responses-only features cost.","Diagram of the Agents SDK runner loop: input, agent, model call, final output, guardrails, and tool calls feeding back into the input","MIT · API pay per token","Agent framework",{"slug":541,"published":542,"minutes":369,"category":7,"tags":543,"keywords":548,"about":555,"sources":565,"cover":586,"og":587,"expertise":62,"locales":588,"lang":64,"title":589,"description":590,"coverAlt":591,"url":592,"pricing":593,"kind":9},"openhands","2026-09-09",[9,544,545,546,547],"Sandboxed execution","Automations","Self-hosted","MIT licence",[541,549,550,551,552,553,22,554],"openhands self-host","open hands coding agent","openhands vs claude code","agent canvas","openhands docker sandbox","openhands cloud pricing",[556,559,562],{"name":557,"url":558},"OpenHands","https:\u002F\u002Fwww.openhands.dev",{"name":560,"url":561},"OpenHands on GitHub","https:\u002F\u002Fgithub.com\u002FOpenHands\u002FOpenHands",{"name":563,"url":564},"Intelligent agent","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FIntelligent_agent",[566,568,571,574,577,580,583],{"title":567,"url":561},"OpenHands README",{"title":569,"url":570},"OpenHands licence (MIT)","https:\u002F\u002Fgithub.com\u002FOpenHands\u002FOpenHands\u002Fblob\u002Fmain\u002FLICENSE",{"title":572,"url":573},"Agent Canvas 1.25.0 release notes","https:\u002F\u002Fdocs.openhands.dev\u002Fopenhands\u002Fusage\u002Fagent-canvas\u002Frelease-notes\u002Fv1.25.0.md",{"title":575,"url":576},"OpenHands sandbox overview","https:\u002F\u002Fdocs.openhands.dev\u002Fopenhands\u002Fusage\u002Fsandboxes\u002Foverview.md",{"title":578,"url":579},"OpenHands quick start","https:\u002F\u002Fdocs.openhands.dev\u002Fopenhands\u002Fusage\u002Finstallation",{"title":581,"url":582},"OpenHands pricing","https:\u002F\u002Fwww.openhands.dev\u002Fpricing",{"title":584,"url":585},"Introducing the OpenHands Index","https:\u002F\u002Fwww.openhands.dev\u002Fblog\u002Fintroducing-the-openhands-index","\u002Fimages\u002Fblog\u002Fopenhands\u002Fcover.webp","\u002Fimages\u002Fblog\u002Fopenhands\u002Fog.jpg",[64,65,66],"OpenHands: the open-source coding agent you operate","OpenHands 1.25.0 is an MIT-licensed coding agent platform with a web canvas, a CLI, sandboxed execution and scheduled automations. A review of where it is strong and where it gets heavy.","Cover artwork for the OpenHands review showing a loop from task to agent to sandboxed run and back","https:\u002F\u002Fgithub.com\u002FAll-Hands-AI\u002FOpenHands","Free · self-host",1791383549006]