Agent Context
File reads, search results, tool output, and thinking accumulate with every turn.
Parsec · Context for coding agents
Less Context.
More Capability.
Give your agent the context it needs to move forward. Parsec trims unused tool output and thinking, so your agent spends less, runs faster, and has more room to work.
Learned Curator
Parsec scores each chunk and removes context the agent is unlikely to use.
Original Content
Kept content stays byte-exact. Your prompts and the agent’s answers stay untouched.
Measured Results
Less context to process. Lower cost, faster runs, and more solved tasks in the benchmark.
SWE-bench Verified
Cheaper. Faster. More Solved.
- Cheaper
- −39%
- $89.65 vs $147.30 total cost
$1.45 per solved task. The lowest of all six arms tested. - Faster
- −25%
- 10.8 hours vs 14.4 hours
The same task set, completed 3.6 hours sooner. - Better
- 62/100
- Up from 57 without compression
Five more working fixes, verified by the official grader.
100 SWE-bench Verified tasks, one fixed model (Claude Sonnet 4.6), the official Docker grader, and cache-aware pricing. Only the compression layer changes.
Less noise, same source
Most Context Never Gets Used.
Across 28,487 real agent traces, 78.4% of trim-eligible context was never used. Parsec's curator scores chunks to predict what your agent will need next.
78.4%
of eligible context went unused in the trace study
- Parsec
- 145 M
- Woz
- 203 M
- Caveman
- 254 M
- Baseline
- 312 M
- Headroom
- 330 M
- RTK
- 361 M
Pricing
Start With Your Next Session
Pro
Free
Plugin + local proxy
- Full learned curator via the hosted scoring API
- Tool-schema pruning
- Governor
Team
Coming Soon
Hosted BYOK gateway
- Your API keys
- Zero local install
- Centralized reporting
Enterprise
Talk To Us
Deployed in your cloud
- The full stack, including the scoring API
- Licensed, containerized checkpoints
- Fine-tuning on traces inside your network
Get Started,
Save more
Give your agent the context it needs to move forward. Parsec trims unused tool output and thinking, so your agent spends less, runs faster, and has more room to work.
Download Now
Which coding agents does it work with?
Claude Code, Codex, and opencode. One local proxy serves all three; the dashboard provides setup instructions for your agent.
Does my code go to your servers?
Hosted scoring receives context chunks over TLS. Model requests go directly to your provider. Enterprise can run scoring inside your VPC.
Can I use my Claude or ChatGPT subscription?
Yes. Local connections use your existing sign-in. The hosted Team gateway accepts API keys only.
What happens if the scoring API is down?
Requests pass through uncompressed, so you can keep working. These events are recorded in the ledger.
How are savings calculated?
Original token counts are compared with billed usage per request. Codex reports billed usage only, because no equivalent token-counting endpoint is available.
Does Parsec train on my data?
Not by default. Telemetry is opt-in, starts disabled, and can be previewed before upload.