⌘ Scoreboard · November 4, 2026
Coding Agents Scoreboard
CLI coding agents and IDE code assistants ranked by AIDiveForge’s listing-data score — completeness, update recency, community signal, and real engagement. Not paid placement.
Ranked by AIDiveForge's listing-data score: data completeness, how recently the listing was updated, community rating, and real visitor engagement. How we rank · No tool can pay for placement.
-
1
Clixad
Clixad is a terminal coding agent with free daily usage, configurable approval modes and optional one-time credit purchases.
Paid Free daily allowance; optional one-time credit packs from US$3Verified Oct 17, 202613.0 score -
2
Airuncode
Airuncode runs agents locally, lets you plug in your own provider keys or on-device models directly, and closes the loop between code generation and testing by repairing failures automatically before surfacing results. The multi-agent debate architecture assigns planning and execution to separate agents that argue toward a solution rather than committing to a first draft. A 3D codebase renderer is the distinguishing visual layer — navigating large projects spatially rather than through flat file trees. The self-hosted path works for teams with hard data-residency requirements. Where the architecture shows its limits: the absence of a public API means Airuncode does not slot into existing CI/CD pipelines without manual bridging, and teams that need programmatic control over agent runs will hit that wall early.
Paid $5.00/30 daysSelf-hostedVerified Sep 9, 202611.8 score -
3
Atlarix
Atlarix is a desktop AI workstation where agents plan, write, test, and debug inside workspaces you control, with a full terminal, an integrated browser the agent can drive, and a visual map of your codebase that updates as things change. You can run managed models, plug in your own API keys, or run models entirely locally — the vendor states code stays on your machine regardless of which path you choose. The approval queue is the core safety mechanism: nothing ships until you accept the diff. Parallel workers let the agent split a task into up to five concurrent efforts, each reporting back independently. The separate Reviewer product reads pull requests on GitHub and posts line-level findings without ever writing to or executing your code.
Paid $19/monthSelf-hostedVerified Aug 28, 202611.4 score -
4
Generative IDE
GIDE is a desktop AI code editor built for teams that cannot or will not send source code to a third-party API. It runs local models fully offline, supports cloud models (Claude, GPT, Gemini) via your own API key, and gates every proposed change through an explicit accept/reject step before writing to disk. The agent reads files, runs tool calls, and shows diffs — all inside the editor. The gate is not optional decoration: the vendor states plan confirmation before edits is a core design constraint. Where it breaks: teams expecting background auto-apply will fight the confirmation model, and the toolchain is new enough that community-sourced workarounds are sparse.
Paid $19.99/moAPISelf-hostedVerified Sep 8, 202611.1 score -
5
SkillHub
SkillHub is a mobile-first coding tutor app built around conversational AI, gamified daily puzzles, and an in-app code playground covering Swift, Python, and JavaScript. You ask a question, the AI explains in plain language, and you can follow up without losing thread — no forum tab-hopping required. The streak mechanic and bite-sized challenges are designed for lunch-break or commute-sized sessions. The free tier caps queries, which means heavy daily use hits a wall fast. There is no API, no web IDE for complex projects, and no path to intermediate or advanced curriculum once the basics click.
Paid Verified Sep 8, 202611.0 score -
6
MonkeysCode
The agent edits code, runs tests, and only commits when the tests pass — so you are not reviewing diffs that silently broke a dependency. Runs are signed and replayable, which means an auditor can inspect exactly what the agent did and why. You can point it at Capuchin (the vendor's own model), Claude, Gemini, ChatGPT, or a local Ollama instance, and swap between them per task without reinstalling anything. Per-task budgets and hard caps mean the cost of an overnight agent run is knowable before it starts. The ceiling arrives when your workflow needs integrations MonkeysCode does not yet expose — at which point you are writing glue code around an IDE rather than composing tools that were built to connect.
Paid $20/monthSelf-hostedVerified Aug 16, 202610.8 score -
7
Symvanta
The core workflow is a graph of call relationships across every repository in a project, queryable via MCP tools like `relate`, `ask_codebase`, and `find_http_route`. An agent checking blast radius before patching a session store, or confirming all 14 call sites before a rename, gets structured answers instead of grep results. The vendor states indexing a 100k-line repo takes around five minutes with no setup, and reports a 47% accuracy improvement on a 2M-line benchmark. Branch state and uncommitted working-tree changes are queryable, which matters when agents continue work mid-flight on feature branches. The ceiling is self-hosting: there is no local deployment path, so teams with air-gapped environments or strict data residency requirements cannot use it.
Paid $19/moAPIVerified Sep 8, 202610.2 score -
8
Command Code
The agent runs in three modes — interactive CLI, headless with a prompt flag for scripted pipelines, and a background sandbox — so it fits scheduled jobs as well as live coding. Learned preferences compile into reusable skills automatically; no rules to write by hand. The team collaboration angle is real: one command pushes your taste profile, the whole team pulls it. Where the walls appear is less documented: open-model tool-calling support is a stated differentiator, but teams hitting complex multi-step agentic chains on open models will need to validate those claims against their specific stack before committing production workloads.
Paid $1/moAPISelf-hostedVerified Jul 16, 202610.2 score -
9
Junie by JetBrains
Junie runs inside JetBrains IDEs or as a standalone CLI, backed by whichever model you bring via API key — no markup on provider rates. The planning mode writes a structured plan to `.junie/plans` before executing, which you can edit, approve, or redirect; the plan files are committable, so the decision trail lives in your repo. Async execution means you can kick off a Spring Boot migration from your laptop and check the pull request from your phone. The ceiling appears when your codebase needs deep multi-repo context or your team relies on editors outside the JetBrains ecosystem — at that point Junie is not in the loop at all.
Paid $8.33/mo or $25.00/moSelf-hostedVerified Aug 16, 202610.0 score -
10
Orca
Orca is an Agent Development Environment built for developers who run Claude Code, Codex, OpenCode, Grok, or any other CLI agent as a daily workflow. It spins each agent into its own git worktree so branches stay isolated, pairs them with Ghostty-inspired terminals and a built-in editor, and surfaces a unified task view so you can see what five agents are doing without switching windows. A mobile companion app for iOS and Android lets you monitor and manage sessions away from your desk. The ceiling appears when your workflow needs deep IDE integration or a plugin ecosystem — Orca is purpose-built for the agent-fleet use case, not a general-purpose editor replacement.
Paid Self-hostedVerified Aug 15, 20269.6 score -
11
LuminaCore AI
LuminaCore AI indexes long-form video through its proprietary DHRUV engine, turning footage into time-coded, queryable structure so teams can ask in natural language and land on a ranked, source-linked moment instead of scrubbing a timeline. The vendor's pilot benchmark cites 372 time-coded results across 20 test queries on 18 hours of source footage, with a median search response around 180 ms — which is the kind of number that matters when a security team is under pressure or a broadcast editor has a slot to fill. Deployment runs inside private VPCs or on-premise, which is what makes it viable for air-gapped defense environments where footage cannot touch a cloud pipeline. There is no public API, so if your workflow needs video intelligence piped into an external system, you are negotiating a custom integration. No free tier exists — access starts with a pilot evaluation through sales.
Paid Self-hostedVerified Sep 25, 20269.5 score -
12
VBAssistant.ai
VBA Assistant is an Excel add-in that lets you describe what you want in plain language and receive generated VBA code, UserForm scaffolding, or a line-by-line explanation without leaving the workbook. The vendor states the backend runs on Azure and does not use submitted code for model training, which matters to teams under data-handling constraints. The free tier is capped at ten requests — enough to evaluate the tool, not enough for a full project sprint. Beyond that cap, continued use requires a paid upgrade. Teams with high daily macro volume or those needing offline capability will hit the ceiling fast and find no self-hosted path forward.
Paid 7.99€/mo or 15.99€/moVerified Jul 16, 20269.4 score -
13
100xprompt
The vendor positions this as sovereign AI infrastructure — meaning the compute, the model, and the data all stay inside your perimeter, whether that perimeter is a company server room or a national-scale government network. The CLI agent handles autonomous coding and deployment tasks without phoning home. Self-hosting is supported, and the API gives your internal tooling a direct integration point. Where this model shows strain is ecosystem breadth: the scraped page content does not surface an established marketplace of pre-built integrations, so teams arriving from richer SaaS ecosystems will build more plumbing themselves. The freemium tier exists, but enterprise-grade air-gap deployments will hit paid-only features quickly.
Paid $20/monthAPISelf-hostedVerified Jul 26, 20269.4 score -
14
Collie
Collie is a local, open-source coding agent that operates directly on your machine — your file system, your signed-in browser session, your real terminal. The core loop is: you describe the task in plain language, Collie does the actual work, then writes a verification step and runs it before declaring the job complete. That proof-first model is what separates it from a chat assistant. It installs as a desktop app on Windows and macOS, or via a single pip command on Linux. No telemetry, no cloud relay — your files and credentials stay local.
Free Open source Self-hostedVerified Aug 14, 20269.3 score -
15
cadre.rocks
The tool wraps Claude Code, Codex, Grok, and OpenAI-compatible CLIs in a single workspace where tasks move through columns, agents run in parallel, and nothing merges until you approve the diff. Your existing CLI logins and API keys stay intact — cadre.rocks sits between you and the agents, not between your machine and the provider. That architecture means token requests go direct to OpenAI or Anthropic with no markup and no intermediary logging. The approval layer is the point: every agent output stops for your sign-off before it ships, which is exactly what breaks in raw terminal workflows at the third concurrent task.
Paid Self-hostedVerified Aug 16, 20269.2 score -
16
Rudder
Rudder wraps Claude Code and Codex agents in a terminal UI that lets you spin up multiple workers in isolated git worktrees, track their progress in parallel, review their output, and merge back to main — all without leaving the terminal. The DAG-based planning layer means complex tasks get broken into steps with explicit dependencies, not a flat prompt you hope executes in order. The worktree isolation model is the real structural win: agents don't step on each other's changes. The ceiling appears when your workflow needs integrations outside the terminal — there is no API surface and no web UI, so anything requiring programmatic triggers or a shared team dashboard requires a different tool entirely.
Free Open source Self-hostedVerified Aug 14, 20269.2 score -
17
Memcode AI
Memcode is a terminal-native coding agent that maintains a persistent memory layer across sessions, so the agent already knows your repo's structure, past decisions, and dead ends when you open it. The TUI ships as a single static binary — no IDE plugin, no browser tab, no Electron overhead. It connects to frontier models, grounds answers in your team's internal docs via DataHub, and runs autonomous scheduled agents for tasks like competitor monitoring or report generation. The memory compounds the longer you use it in a codebase, which is the core differentiation — but that compound value is also the ceiling: a repo the agent has never touched gets the same cold start every other tool gives you.
Free Open source Self-hostedVerified Aug 14, 20269.1 score -
18
MindFlock
MindFlock polls Jira, Linear, GitHub Issues, Shortcut, or Asana for tickets assigned to you, cuts a dedicated git worktree for each, seeds an agent CLI with the ticket's title, description, and acceptance criteria, then runs until you read the diff and decide what ships. Up to five sessions run in parallel on one repo without stepping on each other. The review-and-merge flow is manual by design — commit, push, PR, merge, one click each, never without you. The tool is a local desktop process bound to 127.0.0.1, open-source under Apache 2.0, with no account, no telemetry, and no MindFlock cloud. Your agent still talks to its own provider — Claude to Anthropic, Codex to OpenAI — that call was always yours.
Free Open source Self-hostedVerified Aug 14, 20269.1 score -
19
Zaivern Code
Zaivern Code is a Rust-native cockpit that runs multiple CLI coding agents in a grid view, routes a single broadcast instruction to every active session, and — when you choose — answers Claude Code's confirmation prompts automatically so sessions never stall unattended. The auto-YES switch is off by default and scoped per agent, so you can run one agent on full autopilot while keeping another in manual approval mode for destructive operations. A supervisor layer detects stalls and anomalous exits using deterministic rules, then sends you a notification rather than injecting text directly into any agent's input. The catalog recognizes 29 CLI agents out of the box; anything outside that list can be added as a preset. The included editor covers LSP, Git gutter integration, and Japanese IME — enough to read and patch output without leaving the cockpit.
Free Open source Self-hostedVerified Aug 14, 20269.1 score -
20
Forall
Forall is an Apache-2.0 CLI agent from Astrio that generates spec-driven code alongside machine-checkable proofs, running entirely in your terminal or wiring into Cursor, Claude Code, or Codex via MCP. You describe what the code must do; the agent produces both the implementation and a formal proof you can verify independently. The verification step is not optional decoration — it runs against the spec, so a failing proof surfaces a real logical flaw before the code ships. The docs describe Rust, TypeScript, and Java as the supported targets, which covers a specific but meaningful slice of production codebases. Teams outside those languages hit a hard wall.
Paid Open source APISelf-hostedVerified Jul 18, 20269.0 score -
21
Hanesu
The project borrows from Harness Engineering principles: work is broken into phases with task files, role handoffs, quality gates, and progress artifacts written to disk. Agents using runtimes like OpenCode, Codex, or Claude Code run through that structure rather than a monolithic prompt. The vendor explicitly flags this is not for small, obvious edits — a direct prompt is faster there. Where it earns its place is multi-step refactors, security-sensitive changes, or bugfix workflows where you need the agent to stop, surface what it found, and wait for your sign-off before proceeding.
Free Open source Self-hostedVerified Jul 26, 20268.9 score -
22
Codvian
Codvian runs as a Windows application — available through the Microsoft Store — and lets you wire in your own AI model keys rather than locking you into a bundled provider. The agent handles code editing tasks autonomously, operating locally so your source code does not transit a third-party inference endpoint. Core features are free, which makes it accessible for solo developers evaluating whether a local agent fits their workflow. The scrape-available documentation is thin, and because the product is early-stage with pricing described as 'coming soon,' the feature ceiling for free-tier users is not yet clearly defined. Teams needing Linux or macOS support, or a REST API for pipeline integration, will hit a wall immediately.
Paid Self-hostedVerified Sep 28, 20268.8 score -
23
Grok Build
Grok Build is xAI's terminal-native coding agent: a full-screen TUI that reads your codebase, edits files, runs shell commands, searches the web, and tracks long-running tasks in a loop. It runs interactively for keyboard-driven sessions, headlessly for scripted pipelines, and embeds into editors via the Agent Client Protocol. The open-source, Apache-2.0 codebase is written in Rust and self-hostable. Where it earns trust is in environments where a GUI agent would require a workaround — shell scripts, CI jobs, editor plugins. Where it starts to show limits is in anything requiring a visual interface, fine-grained permission controls per task, or an API surface you can call programmatically.
Free Open source Self-hostedVerified Jul 17, 20268.8 score -
24
CodeTrain
CodeTrain runs a Socratic tutor against your actual repo: it breaks work into small steps, makes developers type every line themselves, and reviews what they wrote without handing over the answer. The local-first free tier keeps code on the machine; the managed tutor sends submitted snippets. A lightweight profile tracks gaps and resurfaces them later through spaced repetition, so a developer who struggled with your auth pattern sees it again before it bites them in production. The team dashboard lets a manager see finished lessons and concept coverage per developer. The ceiling arrives quickly for teams that need structured, multi-week curricula with custom assessments beyond what the Socratic loop can generate.
Paid Self-hostedVerified Jul 21, 20268.7 score -
25
Hotcell
Hotcell is a self-hosted sandbox daemon that provisions isolated containers for agents like Claude Code, Codex, or OpenCode. Each sandbox gets its own cloned workspace on its own branch, a scoped gateway token instead of your real provider key, and a hard spend cap — the actual API credential never enters the container. Five agents against one repo is a single command; teardown revokes every token and cleans every workspace in the same step. The ceiling appears at hardware: you get as many parallel sandboxes as your Mac Mini, Linux VM, or bare-metal box can carry, and no managed scaling layer ships with the open-source daemon.
Paid Open source Self-hostedVerified Aug 14, 20268.7 score
Scores recompute as listings are updated. Sponsored placements (if any) never affect rank. Methodology · Weekly radar