Ross ROSS = Recommend OSS · open-source software intelligence for agents

Paritok-official/paritok-4b-v1

Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent. observed · 2026-08-28

github.com/Paritok-official/paritok-4b-v1 · homepage · Python · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

57/100

  • Activity 99
  • Release rhythm 35
  • Longevity 3

Flags: no_releases young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 49
  • days_rel: n/a
  • days_push: 9
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1449 stars · 138 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Paritok is a non-destructive compression gateway that sits as a drop-in proxy between AI coding agents (Claude Code, Cursor, Codex, OpenHands, or any BASE_URL-configured agent) and their LLM upstream. It uses an open-source 4B model (Qwen3-4B backbone) to strip tool-schema bloat, compress tool results and file reads, and summarize stale history, cutting input-token bills ~25% on turn one to past 85% in long sessions while allowing exact originals to be pulled back on demand.

Use cases

  • reduce LLM API token costs for AI coding agents
  • fit more turns into a fixed context window
  • compress tool schemas and file reads in agent sessions
  • self-host a proxy to cut Claude Code or Cursor token bills
  • summarize stale conversation history without losing recoverable originals
  • recover exact original file content compressed by the gateway
  • filter irrelevant tool definitions per request to shrink prompts

When to choose

  • you run coding agents like Claude Code, Cursor, Codex, or OpenHands and want lower token bills without changing agent code
  • your agent sessions hit context-window saturation and you need ~3x more turns in the same window
  • you want a self-hosted, Apache-2.0 compression layer with on-demand recovery of original content

When to avoid

  • you need zero added latency or cannot run a local 4B model / proxy hop
  • your workflow requires byte-exact prompts upstream at all times with no rewriting
  • you only make short, single-turn LLM calls where compression savings are minimal

Facets

service · maturity active

llm-inference proxy middleware machine-learning developer-tools large-language-models developer-tools infrastructure-as-code self-hosted python self-hosted cross-platform llm-gateway token-optimization context-compression coding-agents drop-in-proxy cost-reduction qwen3-4b prompt-compression ai-agents docker

2 sources

Member repositories

RepositoryRoleHealth v2
Paritok-official/paritok-4b-v1main57

For agents

markdown · JSON · MCP: product_card(name="Paritok-official/paritok-4b-v1")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem