Dev & Engineering terminal-agentdeepseekrustcoding-agenttuici-headlessmcpsandboxing

Orca

A DeepSeek-native terminal coding agent that reads code, edits files, runs commands, and verifies its own work until the task is done or it needs you.

FollowAgents review · FARS-2.1
Not recommended
59/ 100 5-point scale 3.0 / 5
1 2 3 4 5 6
1Trust17 / 29 · 2.9/5

Evidence shows a fairly complete sandbox design: SECURITY.md describes a capability resolver/execution broker, refusal rather than host-shell fallback, non-authoritative project configs, plus landlock/seccompiler dependencies; README offers suggest/auto-edit/full-auto/plan tiers and per-folder /trust. Deductions: a full-auto host-access mode exists with risk boundaries described only at documentation level; no file-edit rollback mechanism is evidenced; copyright is 'blade-deepseek' with unverified publisher, so source attribution is thin.

2Reliability6 / 14 · 2.1/5

Centralized workspace dependency versions, some exact pins (=0.10.4 etc.) and rustls support adequate availability management. Deductions: naming inconsistency — crate 'blade-deepseek', npm package '@blade-ai/orca', SECURITY.md links to a blade-deepseek repo — indicating an incomplete rename; no evidence in the provided files of failure-message design or error-path handling.

3Adaptability12 / 18 · 3.3/5

README clearly covers multi-platform (macOS/Linux/Windows, ARM64/x64), TUI and exec/CI usage, and ACP — enough for full marks on environment fit; /plan read-only mode and a verifier command show capability boundaries. Deductions: trigger precision (when to pick which mode) and audience/scenario depth are thin, with no failure-scenario guidance.

4Convention11 / 18 · 3.1/5

Good information architecture: multilingual README, doc links, SECURITY/CONTRIBUTING/SUPPORT templates; MIT license consistent with Cargo.toml earns full marks. Deductions: no CHANGELOG in the repo (version only as 0.4.24 in Cargo.toml); unstable naming (blade-deepseek vs Orca vs @blade-ai/orca); missing known-limitations documentation; the curl | sh pipe install offers no checksum guidance.

5Effectiveness9 / 13 · 3.5/5

The value proposition is clear (DeepSeek-native, local, prefix-cache-aware prompts, session compression/resume), giving marginal value for the DeepSeek ecosystem. Deductions: no token-cost-control evidence, and output usability is assessable only from documentation; all performance claims lack in-repo benchmarks.

6Verifiability4 / 8 · 2.5/5

README claims are partially cross-checkable against Cargo.toml (version, license, workspace layout) and SECURITY.md. Deductions: only one language variant of the README could be sampled; key claims (sandbox enforcement, npm publication) lack code-level evidence in the provided files; claims and inference are reasonably separated, with no sign of fabricated tests or provenance.

Evidence confidence: Low Reviewed Sep 07, 2026 Reviewed revision 5892a55c3cd4
Before you use it
  • curl | sh and PowerShell remote-script installs cannot be checksum- or integrity-verified in static review; prefer a verified installation method.
  • The full-auto mode grants full host access and is described by SECURITY.md itself as advisory rather than sandboxed — confirm you understand the risk before enabling it.
  • Naming inconsistency (blade-deepseek / Orca / @blade-ai/orca) suggests a complex provenance chain; verify supply-chain attestations (npm provenance, release signing) yourself.
  • Publisher identity is unverified and no response SLA is promised; assess your own support needs before production use.
  • No in-repo CHANGELOG or known-limitations document; consult the external changelog and release notes before upgrading.
Review evidence [1][2][3][4][5][6][7][8]
See the full review method →

What does this agent do, and when should you use it?

Orca (GitHub repo echoVic/orca-agent) is a DeepSeek-native coding agent built in Rust that runs locally under the MIT license. Given a task, it reads code, edits files, runs shell commands, and verifies results, continuing until the task is done or human input is needed. It speaks DeepSeek's reasoning and tool-use semantics directly, with SSE streaming, prefix-cache-friendly prompts, automatic context management, and retry logic. It exposes an interactive TUI (orca), headless execution (orca exec), plus stable JSONL, app-server, and Agent Client Protocol (ACP) contracts for editors, harnesses, and CI. Sessions support resume and fork, with synchronous/async subagents, a persistent goal mode (/goal), automatic project memory, and four permission modes (suggest, sandboxed auto-edit, full-auto, read-only plan) with per-folder trust.

After installation it connects to DeepSeek models via DEEPSEEK_API_KEY, adopting DeepSeek's reasoning/tool-use protocol directly and fully replaying returned reasoning_content across tool turns. Orca reads, searches, edits, and writes code files and runs shell commands; runtime-owned exec_command sessions can stay alive across tool calls, allocate a PTY, and receive input via write_stdin for editors, REPLs, and TUIs, while a background supervisor settles exited sessions and injects a bounded completion notification before the next model turn. Interactive TUI sessions can ask one to four structured clarification questions with described choices, previews, and multi-select. You can verify results before finishing with orca exec --verifier "cargo test" and restore headless sessions with orca exec resume SESSION_ID. It supports sync/async subagents and JavaScript workflows, with durable child continuation via resume_from; /tasks opens live transcripts and exposes stop/resume/retry controls. It learns a bounded set of durable project facts after committed turns (/remember) and retrieves only prompt-relevant facts later. Model-side, DeepSeek V4 thinking is enabled explicitly (reasoning_effort low/high/max), the deepseek-v4 family (Flash, Vision-exp, Pro) offers a 1M-token context and up to 384K output tokens, and JPEG/PNG/GIF/WebP images are accepted in the TUI and from ACP clients, with Ctrl+V clipboard attach and protocol-aware pixel previews. Configuration priority is environment variables, CLI arguments, config files, then defaults; user config lives at ~/.orca/config.toml and trusted projects can supply .orca/config.toml, AGENTS.md, rules, skills, and workflows.

  1. Developers who want a terminal coding agent powered by DeepSeek that reads and edits local code and runs tests to verify its own work
  2. CI/pipeline maintainers running tasks headlessly (e.g., "fix the failing test") with orca exec, integrating via JSONL output and typed exit codes
  3. Engineers using ACP-compatible editors, connecting via orca --mode=acp for an in-editor agent experience
  4. Teams tackling long or parallel work, using subagents and JavaScript workflows with /goal for persistent objectives
  5. Multi-platform users (Windows/macOS/Linux) who rely on unified sandbox permission modes and per-folder trust controls
  6. Workflows needing resumability, using --resume/--fork or orca exec resume to continue conversations up to a message boundary

What are this agent's strengths and limitations?

Pros
  • DeepSeek-native: speaks DeepSeek reasoning/tool-use semantics directly, keeps the Chat Completions transport, and fully replays reasoning_content across tool turns, exploiting 1M context and up to 384K output windows
  • Complete interface surface: one runtime host backs TUI, headless, JSONL, app-server, and ACP contracts, fitting editors, harnesses, and CI
  • Detailed reliability engineering: session switches start replacements before closing runtimes, escape-driven cancellation commits terminal child state, fail-closed continuation recovery restores only digest-verified checkpoints, and budget stops settle tools and exit 4 with a typed terminal
  • Granular permission model: suggest, sandboxed auto-edit, full-auto, and read-only plan modes plus per-folder trust, with AppContainer isolation and restricted sessions on Windows
  • Strong multi-platform support: the npm package covers macOS/Linux/Windows on ARM64 and x64, with explicit Windows handling of PowerShell 7/5.1/cmd.exe
Limitations
  • Model lock-in to DeepSeek: core operation depends on DEEPSEEK_API_KEY and DeepSeek semantics (e.g., reasoning_content replay); no alternative model-provider adapter path is documented
  • The README references deepseek-v4-family models (Flash, Vision-exp, Pro) and V4 thinking; availability and pricing of those models to you should be confirmed before adopting
  • Advanced capabilities (sandbox, subagent continuation, workflows, memory, MCP) require a trusted project with .orca/config.toml and related configuration, creating initial setup cost
  • Windows behavior branches: PowerShell 7 is preferred, restricted sessions fall back to cmd.exe when it is missing, and 5.1 is limited to modes without AppContainer isolation
  • Image attachments share a 5 MiB total limit; SSH sessions without a graphical clipboard must paste or reference remote paths, and terminals without image protocols degrade to low-resolution cell previews

How do you install or deploy this agent?

Install globally via npm (macOS/Linux/Windows on ARM64 and x64): npm install -g @blade-ai/orca. Or install the native binary directly: on macOS/Linux run curl -fsSL https://orcaagent.dev/install.sh | sh; on Windows PowerShell run irm https://orcaagent.dev/install.ps1 | iex. From a Windows project directory, provision the restricted sandbox with & ([scriptblock]::Create((irm https://orcaagent.dev/install.ps1))) -SetupSandbox. Prebuilt archives are also available on GitHub Releases.

How do you use this agent?

1) Set the key: export DEEPSEEK_API_KEY=sk-... (Windows PowerShell: $env:DEEPSEEK_API_KEY = "sk-..."). 2) Run orca to open the TUI; or orca exec "fix the failing test" for headless runs; or orca exec --verifier "cargo test" "fix it" to verify before finishing. 3) Resume with orca --resume [SESSION_ID], fork with --fork SESSION_ID, or continue headless sessions with orca exec resume SESSION_ID "continue" (use --last for the most recent, --resume-at MID to stop at a message boundary). 4) In the TUI, @ searches files/skills/plugins/MCP resources; /plan for read-only planning, /goal for a persistent objective, /tasks for subagents and background commands, /trust for sandbox permissions, /config for session settings. 5) Configuration lives in ~/.orca/config.toml; tune thinking depth via reasoning_effort in config.toml or ORCA_REASONING_EFFORT.

FAQ

Must I use DeepSeek? Can I swap in another model provider?
Yes. Orca is DeepSeek-native and depends on DEEPSEEK_API_KEY and DeepSeek's reasoning/tool-use semantics; the documentation offers no adapter path for other model providers.
Can it run unattended in CI, and how do I bound cost and duration?
Yes. Use orca exec headlessly and set explicit budgets via --max-turns, --max-tool-calls, --max-cost-usd, and --max-wall-time-secs; a budget stop settles the current tool, creates a checkpoint, and exits 4 with a typed terminal in the JSONL stream.
How risky is it? Can I limit file edits and command execution?
There are suggest, sandboxed auto-edit, full-auto, and read-only plan modes, plus per-folder /trust permission management; Windows offers AppContainer-isolated restricted sessions.
Can I recover after exiting or a crash?
Yes. On exit Orca prints the exact orca --resume <SESSION_ID> command; headless sessions restore with orca exec resume SESSION_ID (or --last, or --resume-at MID) under a fresh budget scope. Continuation recovery is fail-closed and restores only digest-verified checkpoints.
Does it support image input, and what are the limits?
Yes. TUI and ACP clients accept JPEG/PNG/GIF/WebP; the vision model consumes images directly while auto/Pro/Flash run task-aware vision analysis. Inline attachments share a 5 MiB limit; Kitty/Ghostty/iTerm2/WezTerm get native pixel previews while other terminals fall back to low-resolution true-color cells.

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related agents