tgv is a terminal genome viewer built for humans and agents together. It navigates genomes with vim-style commands and mouse support, reads BAM, VCF, BCF, BED and bigBed, object storage over s3, and any UCSC reference genome, and runs fast enough that an SSH session is no longer a black box. For agent work it exposes the underlying data engine through MCP, so a multi-omics analysis is a few lines of SQL instead of glue scripts chaining samtools, bcftools and awk, with no off-by-one bugs from mixing 0-based and 1-based tools. Install with cargo, brew or bioconda.
Be the first to rate tgv. Your feedback helps other users decide.
Open a BAM or VCF in the terminal and move with vim-style keys or the mouse.
Let an agent run SQL against the exposed data engine rather than chaining command-line tools.
Point it at s3 or a UCSC reference genome without downloading first.
Similar tools in the same category — compare side-by-side
Pose Lab gives a model measured spatial answers instead of guesses when posing first-person arms and...
Galahad is long-term memory for AI agents, distributed as the galahad-kv Python package on PyPI. It ...
Hapsland catches questionable data and code decisions while your coding agent is still working. It a...
Guides and comparisons about code tools
Ten launches that keep the model, the index and the facts on your own machine, from search that admits no match to GPU training in CUDA.
Ten October 2026 agent infrastructure launches: local inference engines, sandboxes that report their isolation boundary, agent memory and MCP testing.
Eight local inference projects that fit big models into small memory: a 26B model in 2 GB, MoE weight streaming, a console as a server and sub-1-bit compression
Nine tools for supervising coding agents: phone alerts when an agent blocks, review inboxes, menu-bar contacts, shared scratchpads and team boards.
Nine tools that constrain what an agent can produce and reach: slop-detecting lint rules, declared sandbox tiers, cheaper crawling and signed messaging.
