Products

condense

AI-nativeSkill

Less context. Same Agent.

condense.chat SourceAI Models & Agents / Prompts, Evals & LLM Observability

AI Benchmark
Desktop
Mobile
Monthly visits
None yet
No traffic data yet
Public revenue
Undisclosed
No public revenue evidence yet
Entry price
$5/mo
Lower than 91% of peersNiche median $21.6/mo
Creators
condense-chat
GitHub @condense-chat
Launched
4d ago
2026-11-10 · Est.

Traffic

Last 12 months
Monthly visits

No traffic data yet.

Events1 marketing move

Marketing moves

Launches, search & content, referrals, promotions

  • Launched on Findly.toolsLaunch

    condense.chat — Get up to 3x more Claude Code per plan and lower AI agent API bills by managing and compressing the context sent on every LLM call.

    Nov 10 · 4d agoLaunch page

Third-party reviews & case dossiers

Acquisition breakdowns, engineer reviews & open-source metrics
Findly.tools
2026-11-10Source
What engineers like:
condense.chat is a drop-in proxy that manages and compresses the context your AI agents send on every LLM call. Long agent sessions resend the same file reads, diffs, tool results and history on every turn, so the bill grows with every step. condense cuts that down before the request reaches the provider, and the agent works the same. The open-source dense CLI (MIT) runs Claude Code, Codex or OpenCode through condense. Run dense claude and keep working. On a Claude subscription, dense usage shows how much of your plan you used and what the same work would have used without condense. On long sessions that adds up to as much as 3x more Claude Code per plan. Change one base URL. It works with Anthropic, OpenAI (Chat Completions and Responses), Claude and Gemini on Vertex AI, and Amazon Bedrock. Your provider key is forwarded as usual and never stored, so your provider still bills you directly, just for fewer tokens. The benchmark is public and reproducible. Two models: Helene 1.1 for everyday traffic and Adeline 1 for long-running sessions. Free for personal use. Teams integrating it into their product pay a share of what it saves. Docs

Open Source & Agent Ecosystem

GitHub · MCP / Skill
condense-chat/minmax-bench
GitHub Stars
Public repo
Forks
—
License
See repository
Primary language
—
Browse peer open-source projects →

Agent, MCP & Developer Integration

Agent SkillCLI / SDKAPI
Integration docs
Ecosystem & integrations:
Claude CodeCodexOpenCodeAnthropicOpenAIClaude
Exposed tool capabilities:
Prompt CompressionShrink the billRealtime savings dashboardSavings reported by keyCentralized billingSeat management
Browse developer & CLI tools →

Traffic sources

Traffic breakdown

No traffic channel or country breakdown data for this website yet.

View similar products ↓

Search

Domain authority —Domain registered 2026-04-19

No search keyword data for this website yet.

Traffic data: Vaneform

Pricing

Free
Free
Starter
$5/mo
Pro
$20/mo
Max
$50/mo
Team
$5/mo
For teams of 5–150
Custom
Contact sales
For 150+ seats & custom terms

Trial: None · Free tier included · 4 paid tiers ($5–$50) · Enterprise custom tier · Observed 2026-11-13 · Pricing page

Entry price $5/mo, Lower than 91% of peers; “Prompts, Evals & LLM Observability” median is $21.6/mo.View pricing benchmark

Pages & changes

Tracked since 2026-11-10

Key pages

Weekly snapshots

Changes

No pricing, plan, or positioning changes detected since tracking started.

Questions & evidence

How much does condense cost?
Free: Free; Starter: $5/mo; Pro: $20/mo; Max: $50/mo; Team: $5/mo; Custom: Contact sales. Observed 2026-11-13. Check the source for current billing terms, usage limits and taxes.Source
What is condense and what platforms does it support?
condense is catalogued under Prompts, Evals & LLM Observability: Less context. Same Agent.. Supported platforms: CLI / SDK, API.
Is condense open source?
condense has a public repository (https://github.com/condense-chat/minmax-bench) with its source repository published.Source

Related products in this category

AI Models & Agents / Prompts, Evals & LLM Observability

These products share a catalog category. Compare customer tasks, features and deployment requirements before treating them as alternatives.