Get This Tool
Excalibur
Pricing
- Model
- Free
Summary
Most AI coding agents hand you a diff and walk away — no context on whether the feature was worth building, no verification that it actually works, no audit trail when something breaks in production. Excalibur is built around the premise that the diff is the middle of the story, not the end.
Excalibur runs the full cycle: Discovery weighs scope and risk before a line is written, a swarm of agents in isolated worktrees handles the build, and an adversarial verification mesh checks typed claims before anything ships. Every run is recorded as an immutable, append-only event log — scrub it like a video, fork from any step, or share a read-only link. The local web dashboard exposes live swarm chronograms and cost tracking without a SaaS account. The ceiling appears on teams whose workflow lives outside the CLI — no hosted API means you cannot call Excalibur from a pipeline without scripting around it yourself.
Bottom line: Pick this when you need a local, auditable, model-agnostic agent that covers discovery through audit on a single repo; plan a different approach when your team needs a hosted API or programmatic integration into an existing CI orchestration layer.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Discovery phase weighs scope, evidence, and risk before any code runs, so you kill underspecified work before it costs you a sprint rather than after it ships.
- Immutable event log doubles as live view, replay, and audit trail from one source of truth, so post-incident reviews have a byte-identical record of every agent decision instead of reconstructed logs.
- Adversarial verification mesh gates each run on typed claims (tests_passed, type_safe, no_secrets), so broken or insecure patches do not reach the pull request stage.
- Provider-agnostic model routing with per-session switching, so a cost spike on one provider is a config change rather than a migration project.
- Local web dashboard with swarm chronograms and cost tracking requires no SaaS account, so teams with data-residency constraints or air-gapped repos get full observability without sending data offsite.
Cons
Sign in to edit- No hosted API is available — triggering Excalibur from an existing CI pipeline or external orchestration system requires shell-scripting around the CLI, which means teams maintaining a mature pipeline end up owning that glue layer themselves.
- The agentic swarm model is sized to the task automatically, but teams that need fine-grained control over parallelism or custom agent topologies have no documented extension point for that in the scraped content — teams with complex multi-repo orchestration needs will hit this ceiling and evaluate purpose-built orchestration frameworks instead.
- Beta status is stated on the page — production teams that cannot tolerate breaking changes in CLI behavior or event-log schema between releases will need to pin versions and monitor the changelog actively, or defer adoption until the API surface stabilizes.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- macOS, Linux, Windows (via npm)
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-07-07T08:03:10.693Z
Best For
Who it's for
- Product engineers needing end-to-end agentic workflows
- Teams wanting local, auditable, model-agnostic tooling
- Repositories requiring discovery and quality gates before implementation
What it does well
- Adding rate limiting to an API with full verification
- Generating scoped work items from ideas before coding
- Running multi-agent swarms for complex changes
- Reviewing and auditing agent-produced patches
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Excalibur
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Excalibur free?
- Yes — Excalibur is fully free to use. There is no paid tier.
- Is Excalibur open source?
- Yes. Excalibur is open source.
- Can I self-host Excalibur?
- Yes. Excalibur supports self-hosting on your own infrastructure.
- What platforms does Excalibur support?
- Excalibur is available on: macOS, Linux, Windows (via npm).
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Agents that only write code leave you managing the bookends yourself — scoping what to build, verifying it works, documenting it honestly, and auditing what shipped. Excalibur covers that full cycle: Discovery analyzes scope, evidence, and risk before producing a scoped work item (with a recommendation of build, validate, or don’t-build), then Plan → Build → Test → Docs → Review → Ship → Audit runs as a structured pipeline. Large tasks auto-size into a swarm of agents running in isolated worktrees, coordinated through a verification mesh that gates completion on typed claims like tests_passed, type_safe, and no_secrets.
The defining technical feature is the immutable, append-only event log. The vendor describes this as a single stream that serves simultaneously as the live terminal view, replay scrubber, browser dashboard, and audit trail — byte-identical across all four surfaces. You can rewind mid-session with Esc-Esc, fork a new run from any cached step (replaying the good prefix for free), or mint a read-only share link from the local dashboard. The docs describe this as architecturally distinct from other agents, which reconstruct state rather than preserving it.
Excalibur is self-hosted, Apache-2.0 licensed, and installs via a single npm command. It is provider-agnostic — the docs describe support for OpenAI-compatible endpoints (including Azure), Anthropic, Ollama, and others, with model switching mid-session via /models. Keys live in an env file and never touch the repo. The local board (excalibur serve) runs as one process on localhost, giving teams Kanban work items, live cost tracking, and swarm chronograms without creating an account. The tool is positioned for product engineers and teams that need end-to-end traceability on a local repository — not for teams that need a hosted API surface or plug-and-play CI integration.