Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.
Python agent-skillsai-agentsaudio-processingcaptionsclaude-codecodexcoding-agentcursorffmpegloudness-normalizationmcpmcp-servermodel-context-protocolpythonsubtitlestranscodingvideovideo-editingvideo-processingwhisper
Commits on main
fix: render.py refuses unknown project keys, ctx= reaches write_plan and the exit hook, --crf mark on every tool with --quality, time refusals say not a time (#211)
7834cdf claude[bot] committed 2 months ago
docs: eval iteration 10 at 1.10.0, README catches up with 1.8-1.10, PR checklist names the README (#210)
f693ad0 claude[bot] committed 2 months ago
feat: deprecated list in the contract, ctx= on run/emit/die/info, FFMPEG_SKILL_MCP_LEAN, NO_OVERWRITE as the agent setting, eval-9 follow-ups (#209)
4053fda claude[bot] committed 2 months ago
docs: eval iteration 9 at 1.9.0 (108 runs, independent grader, trigger set) (#208)
d7baf64 claude[bot] committed 2 months ago
fix: @fps in caption cue files, one @ only, time_arg() in metadata/multicam/speedramp, render normalize default documented (#207)
b2dd9b9 claude[bot] committed 2 months ago
feat: one time grammar (@fps, time_arg in broll/cut/freeze), probe hdr_signal, eval-8 follow-ups (#206)
8dccba2 claude[bot] committed 2 months ago
fix: seventh review (--normalize temp name, --codec edges, contract) and eval-8 follow-ups (#204)
d69bc5a claude[bot] committed 2 months ago
docs: evals iteration 8 at 1.8.0 (108 runs, independent grader, trigger set) (#205)
eb340e6 claude[bot] committed 2 months ago
feat: --codec h264|hevc|av1|prores and --quality on every re-encoding tool, resolved in encoder_args() (#203)
3806959 claude[bot] committed 2 months ago
docs: roadmap from 1.7.1 to 1.20.0 and what 2.0 removes (#201)
13fd8b6 claude[bot] committed 2 months ago
fix: check.py judgement rows are WARN without a named platform; render.py export.normalize (#202)
06fc105 claude[bot] committed 2 months ago
fix: eval-7 follow-ups -- export --normalize, render frame from the export preset, report language and labels on failures (#200)
58838fe claude[bot] committed 2 months ago
docs: evals iteration 7 at 1.7.0 (108 runs, independent grader, trigger set) (#199)
3f92d01 claude[bot] committed 2 months ago
feat: every writing tool reports what it verified (verified, verification); sixth-review fixes to the plan edges (#197)
d631959 claude[bot] committed 2 months ago
docs: record the 2.0 design decisions (time grammar, encoder abstraction, Context) (#198)
7a46c22 claude[bot] committed 2 months ago
feat: --plan FILE writes the dry run as a plan that render.py executes (#196)
cf579ac claude[bot] committed 2 months ago
fix: eval-6 follow-ups -- fade-in-only --fade, export measures platform loudness, cut names the lossless alternative, report language on short jobs (#195)
84d12c4 claude[bot] committed 2 months ago
fix: fifth review -- render self-overwrite, fit trim subtitles, caption transcribe under dry-run, and nine smaller items (#194)
42b29da claude[bot] committed 2 months ago